@llamaindex/llama-cloud-mcp 2.19.0 → 2.20.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/code-tool-worker.d.mts.map +1 -1
- package/code-tool-worker.d.ts.map +1 -1
- package/code-tool-worker.js +11 -14
- package/code-tool-worker.js.map +1 -1
- package/code-tool-worker.mjs +11 -14
- package/code-tool-worker.mjs.map +1 -1
- package/local-docs-search.d.mts.map +1 -1
- package/local-docs-search.d.ts.map +1 -1
- package/local-docs-search.js +389 -70
- package/local-docs-search.js.map +1 -1
- package/local-docs-search.mjs +389 -70
- package/local-docs-search.mjs.map +1 -1
- package/methods.d.mts.map +1 -1
- package/methods.d.ts.map +1 -1
- package/methods.js +55 -73
- package/methods.js.map +1 -1
- package/methods.mjs +55 -73
- package/methods.mjs.map +1 -1
- package/package.json +6 -6
- package/server.js +1 -1
- package/server.mjs +1 -1
- package/src/code-tool-worker.ts +11 -14
- package/src/local-docs-search.ts +456 -70
- package/src/methods.ts +55 -73
- package/src/server.ts +1 -1
package/src/local-docs-search.ts
CHANGED
|
@@ -67,9 +67,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
67
67
|
'external_file_id?: string;',
|
|
68
68
|
],
|
|
69
69
|
response:
|
|
70
|
-
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
70
|
+
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
71
71
|
markdown:
|
|
72
|
-
"## create\n\n`client.files.create(file: string, purpose: string, organization_id?: string, project_id?: string, external_file_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**post** `/api/v1/beta/files`\n\nUpload a file using multipart/form-data.\n\nSet `purpose` to indicate how the file will be used:\n`user_data`, `parse`, `extract`, `classify`, `split`,\n`sheet`, or `agent_app`.\n\nReturns the created file metadata including its ID for use\nin subsequent parse, extract, or classify operations.\n\n### Parameters\n\n- `file: string`\n The file to upload\n\n- `purpose: string`\n The intended purpose of the file. Valid values: 'user_data', 'parse', 'extract', 'split', 'classify', 'sheet', 'agent_app'. This determines the storage and retention policy for the file.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `external_file_id?: string`\n The ID of the file in the external system\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst file = await client.files.create({ file: fs.createReadStream('path/to/file'), purpose: 'purpose' });\n\nconsole.log(file);\n```",
|
|
72
|
+
"## create\n\n`client.files.create(file: string, purpose: string, organization_id?: string, project_id?: string, external_file_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**post** `/api/v1/beta/files`\n\nUpload a file using multipart/form-data.\n\nSet `purpose` to indicate how the file will be used:\n`user_data`, `parse`, `extract`, `classify`, `split`,\n`sheet`, or `agent_app`.\n\nReturns the created file metadata including its ID for use\nin subsequent parse, extract, or classify operations.\n\n### Parameters\n\n- `file: string`\n The file to upload\n\n- `purpose: string`\n The intended purpose of the file. Valid values: 'user_data', 'parse', 'extract', 'split', 'classify', 'sheet', 'agent_app'. This determines the storage and retention policy for the file.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `external_file_id?: string`\n The ID of the file in the external system\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_size?: number`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst file = await client.files.create({ file: fs.createReadStream('path/to/file'), purpose: 'purpose' });\n\nconsole.log(file);\n```",
|
|
73
73
|
perLanguage: {
|
|
74
74
|
python: {
|
|
75
75
|
method: 'files.create',
|
|
@@ -124,9 +124,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
124
124
|
'page_token?: string;',
|
|
125
125
|
],
|
|
126
126
|
response:
|
|
127
|
-
'{ items: { id: string; name: string; project_id: string; download_url?: object; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }[]; next_page_token?: string; total_size?: number; }',
|
|
127
|
+
'{ items: { id: string; name: string; project_id: string; download_url?: object; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }[]; next_page_token?: string; total_size?: number; }',
|
|
128
128
|
markdown:
|
|
129
|
-
"## query\n\n`client.files.query(organization_id?: string, project_id?: string, filter?: { data_source_id?: string; external_file_id?: string; file_ids?: string[]; file_name?: string; only_manually_uploaded?: boolean; project_id?: string; }, order_by?: string, page_size?: number, page_token?: string): { items: object[]; next_page_token?: string; total_size?: number; }`\n\n**post** `/api/v1/beta/files/query`\n\nQuery files with filtering and pagination. Deprecated: use `GET /files`.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `filter?: { data_source_id?: string; external_file_id?: string; file_ids?: string[]; file_name?: string; only_manually_uploaded?: boolean; project_id?: string; }`\n Filter parameters for file queries.\n - `data_source_id?: string`\n Filter by data source ID\n - `external_file_id?: string`\n Filter by external file ID\n - `file_ids?: string[]`\n Filter by specific file IDs\n - `file_name?: string`\n Filter by file name\n - `only_manually_uploaded?: boolean`\n Filter only manually uploaded files (data_source_id is null)\n - `project_id?: string`\n Filter by project ID\n\n- `order_by?: string`\n A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order.\n\n- `page_size?: number`\n The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum.\n\n- `page_token?: string`\n A page token, received from a previous list call. Provide this to retrieve the subsequent page.\n\n### Returns\n\n- `{ items: { id: string; name: string; project_id: string; download_url?: object; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }[]; next_page_token?: string; total_size?: number; }`\n Paginated list of files.\n\n - `items: { id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }[]`\n - `next_page_token?: string`\n - `total_size?: number`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.files.query();\n\nconsole.log(response);\n```",
|
|
129
|
+
"## query\n\n`client.files.query(organization_id?: string, project_id?: string, filter?: { data_source_id?: string; external_file_id?: string; file_ids?: string[]; file_name?: string; only_manually_uploaded?: boolean; project_id?: string; }, order_by?: string, page_size?: number, page_token?: string): { items: object[]; next_page_token?: string; total_size?: number; }`\n\n**post** `/api/v1/beta/files/query`\n\nQuery files with filtering and pagination. Deprecated: use `GET /files`.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `filter?: { data_source_id?: string; external_file_id?: string; file_ids?: string[]; file_name?: string; only_manually_uploaded?: boolean; project_id?: string; }`\n Filter parameters for file queries.\n - `data_source_id?: string`\n Filter by data source ID\n - `external_file_id?: string`\n Filter by external file ID\n - `file_ids?: string[]`\n Filter by specific file IDs\n - `file_name?: string`\n Filter by file name\n - `only_manually_uploaded?: boolean`\n Filter only manually uploaded files (data_source_id is null)\n - `project_id?: string`\n Filter by project ID\n\n- `order_by?: string`\n A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order.\n\n- `page_size?: number`\n The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum.\n\n- `page_token?: string`\n A page token, received from a previous list call. Provide this to retrieve the subsequent page.\n\n### Returns\n\n- `{ items: { id: string; name: string; project_id: string; download_url?: object; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }[]; next_page_token?: string; total_size?: number; }`\n Paginated list of files.\n\n - `items: { id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }[]`\n - `next_page_token?: string`\n - `total_size?: number`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.files.query();\n\nconsole.log(response);\n```",
|
|
130
130
|
perLanguage: {
|
|
131
131
|
python: {
|
|
132
132
|
method: 'files.query',
|
|
@@ -184,9 +184,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
184
184
|
'project_id?: string;',
|
|
185
185
|
],
|
|
186
186
|
response:
|
|
187
|
-
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
187
|
+
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
188
188
|
markdown:
|
|
189
|
-
"## list\n\n`client.files.list(expand?: string[], external_file_id?: string, file_ids?: string[], file_name?: string, order_by?: string, organization_id?: string, page_size?: number, page_token?: string, project_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**get** `/api/v1/beta/files`\n\nList files with optional filtering and pagination.\n\nFilter by `file_name`, `file_ids`, or `external_file_id`.\nSupports cursor-based pagination and custom ordering.\n\n### Parameters\n\n- `expand?: string[]`\n Fields to expand on each file.\n\n- `external_file_id?: string`\n Filter by external file ID.\n\n- `file_ids?: string[]`\n Filter by specific file IDs.\n\n- `file_name?: string`\n Filter by file name (exact match).\n\n- `order_by?: string`\n Order the results. One of 'name' (ascending), 'id' (ascending) or 'created_at' (descending). An explicit asc/desc modifier and multi-field ordering are not supported; anything else is rejected.\n\n- `organization_id?: string`\n\n- `page_size?: number`\n The maximum number of items to return. Defaults to 50, maximum is 1000.\n\n- `page_token?: string`\n A page token received from a previous list call. Provide this to retrieve the subsequent page.\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const fileListResponse of client.files.list()) {\n console.log(fileListResponse);\n}\n```",
|
|
189
|
+
"## list\n\n`client.files.list(expand?: string[], external_file_id?: string, file_ids?: string[], file_name?: string, order_by?: string, organization_id?: string, page_size?: number, page_token?: string, project_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**get** `/api/v1/beta/files`\n\nList files with optional filtering and pagination.\n\nFilter by `file_name`, `file_ids`, or `external_file_id`.\nSupports cursor-based pagination and custom ordering.\n\n### Parameters\n\n- `expand?: string[]`\n Fields to expand on each file.\n\n- `external_file_id?: string`\n Filter by external file ID.\n\n- `file_ids?: string[]`\n Filter by specific file IDs.\n\n- `file_name?: string`\n Filter by file name (exact match).\n\n- `order_by?: string`\n Order the results. One of 'name' (ascending), 'id' (ascending) or 'created_at' (descending). An explicit asc/desc modifier and multi-field ordering are not supported; anything else is rejected.\n\n- `organization_id?: string`\n\n- `page_size?: number`\n The maximum number of items to return. Defaults to 50, maximum is 1000.\n\n- `page_token?: string`\n A page token received from a previous list call. Provide this to retrieve the subsequent page.\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_size?: number`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const fileListResponse of client.files.list()) {\n console.log(fileListResponse);\n}\n```",
|
|
190
190
|
perLanguage: {
|
|
191
191
|
python: {
|
|
192
192
|
method: 'files.list',
|
|
@@ -233,9 +233,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
233
233
|
qualified: 'client.files.retrieve',
|
|
234
234
|
params: ['file_id: string;', 'expand?: string[];', 'organization_id?: string;', 'project_id?: string;'],
|
|
235
235
|
response:
|
|
236
|
-
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
236
|
+
'{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }',
|
|
237
237
|
markdown:
|
|
238
|
-
"## retrieve\n\n`client.files.retrieve(file_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**get** `/api/v1/beta/files/{file_id}`\n\nGet file metadata by ID.\n\n### Parameters\n\n- `file_id: string`\n\n- `expand?: string[]`\n Fields to expand.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst file = await client.files.retrieve('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(file);\n```",
|
|
238
|
+
"## retrieve\n\n`client.files.retrieve(file_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; name: string; project_id: string; download_url?: presigned_url; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n\n**get** `/api/v1/beta/files/{file_id}`\n\nGet file metadata by ID.\n\n### Parameters\n\n- `file_id: string`\n\n- `expand?: string[]`\n Fields to expand.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; project_id: string; download_url?: { expires_at: string; url: string; form_fields?: object; }; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; purpose?: string; }`\n An uploaded file.\n\n - `id: string`\n - `name: string`\n - `project_id: string`\n - `download_url?: { expires_at: string; url: string; form_fields?: object; }`\n - `expires_at?: string`\n - `external_file_id?: string`\n - `file_size?: number`\n - `file_type?: string`\n - `last_modified_at?: string`\n - `purpose?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst file = await client.files.retrieve('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(file);\n```",
|
|
239
239
|
perLanguage: {
|
|
240
240
|
python: {
|
|
241
241
|
method: 'files.retrieve',
|
|
@@ -388,16 +388,16 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
388
388
|
'file_input: string;',
|
|
389
389
|
'organization_id?: string;',
|
|
390
390
|
'project_id?: string;',
|
|
391
|
-
"configuration?: { categories: { name: string; description?: string; }[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; };",
|
|
391
|
+
"configuration?: { categories: { name: string; description?: string; }[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; };",
|
|
392
392
|
'configuration_id?: string;',
|
|
393
393
|
'transaction_id?: string;',
|
|
394
394
|
'webhook_configuration_ids?: string[];',
|
|
395
395
|
'webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[];',
|
|
396
396
|
],
|
|
397
397
|
response:
|
|
398
|
-
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }",
|
|
398
|
+
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }",
|
|
399
399
|
markdown:
|
|
400
|
-
"## create\n\n`client.split.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { categories: object[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; }, configuration_id?: string, transaction_id?: string, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n\n**post** `/api/v1/split/jobs`\n\nCreate a split job.\n\n## Document input\n\nSet `file_input` to a file ID or a completed parse job ID (`pjb-...`). Supplying a parse job reuses its output instead of reading the document again.\n\n## Page selection\n\n`configuration.target_pages` selects which pages of a supplied parse job to split (1-based; `1-50`, `1,3,5-7`). Pages are read in ascending document order, and each segment's `pages` are the parse job's own page numbers, so segments map straight back to the original document. Requires a parse job as `file_input`; passing it with a file ID returns 400.\n\n## Parse settings\n\n`configuration.parse_tier` and `configuration.parse_config_id` control how the document is read before splitting; both are ignored when a parse job is supplied. A parse configuration restricted to a page subset (`target_pages` or `max_pages`) is rejected, since split results always number pages relative to the full document.\n\nThe job runs asynchronously. Poll `GET /split/jobs/{split_job_id}` or register a webhook to monitor completion.\n\n### Parameters\n\n- `file_input: string`\n File ID or parse job ID\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { categories: { name: string; description?: string; }[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; }`\n Split configuration with categories and splitting strategy.\n - `categories: { name: string; description?: string; }[]`\n Categories to split documents into.\n - `parse_config_id?: string`\n Saved parse configuration ID to control how the document is parsed before splitting. Takes precedence over parse_tier. Configurations that restrict pages (`target_pages` or `max_pages` on the parse configuration) are rejected: split results number pages relative to the full document. Ignored when a completed parse job is supplied as file_input.\n - `parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'`\n Parse tier used to read the document before splitting. Defaults to fast. Ignored when a completed parse job is supplied as file_input.\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n Strategy for splitting documents.\n - `target_pages?: string`\n Comma-separated page numbers or ranges to split (1-based). Pages are split in the order listed. Omit to split all pages. Requires a completed parse job as file_input.\n - `version?: string`\n Split version to run. Omit for the current release. Preview versions are selectable by name and never resolved automatically.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `transaction_id?: string`\n Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored.\n\n- `webhook_configuration_ids?: string[]`\n IDs of saved webhook configurations to notify for this job.\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.split.create({ file_input: 'dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee' });\n\nconsole.log(split);\n```",
|
|
400
|
+
"## create\n\n`client.split.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { categories: object[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; }, configuration_id?: string, transaction_id?: string, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: object[]; }`\n\n**post** `/api/v1/split/jobs`\n\nCreate a split job.\n\n## Document input\n\nSet `file_input` to a file ID or a completed parse job ID (`pjb-...`). Supplying a parse job reuses its output instead of reading the document again.\n\n## Page selection\n\n`configuration.target_pages` selects which pages of a supplied parse job to split (1-based; `1-50`, `1,3,5-7`). Pages are read in ascending document order, and each segment's `pages` are the parse job's own page numbers, so segments map straight back to the original document. Requires a parse job as `file_input`; passing it with a file ID returns 400.\n\n## Parse settings\n\n`configuration.parse_tier` and `configuration.parse_config_id` control how the document is read before splitting; both are ignored when a parse job is supplied. A parse configuration restricted to a page subset (`target_pages` or `max_pages`) is rejected, since split results always number pages relative to the full document.\n\nThe job runs asynchronously. Poll `GET /split/jobs/{split_job_id}` or register a webhook to monitor completion.\n\n### Parameters\n\n- `file_input: string`\n File ID or parse job ID\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { categories: { name: string; description?: string; }[]; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; }`\n Split configuration with categories and splitting strategy.\n - `categories: { name: string; description?: string; }[]`\n Categories to split documents into. Names must be unique; 'uncategorized' is reserved unless allow_uncategorized is 'forbid'.\n - `parse_config_id?: string`\n Saved parse configuration ID to control how the document is parsed before splitting. Takes precedence over parse_tier. Configurations that restrict pages (`target_pages` or `max_pages` on the parse configuration) are rejected: split results number pages relative to the full document. Ignored when a completed parse job is supplied as file_input.\n - `parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'`\n Parse tier used to read the document before splitting. Defaults to fast. Ignored when a completed parse job is supplied as file_input.\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n Strategy for splitting documents.\n - `target_pages?: string`\n Comma-separated page numbers or ranges to split (1-based). Pages are split in the order listed. Omit to split all pages. Requires a completed parse job as file_input.\n - `version?: string`\n Split version to run. Omit for the current release. Preview versions are selectable by name and never resolved automatically.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `transaction_id?: string`\n Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored.\n\n- `webhook_configuration_ids?: string[]`\n IDs of saved webhook configurations to notify for this job.\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n - `warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.split.create({ file_input: 'dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee' });\n\nconsole.log(split);\n```",
|
|
401
401
|
perLanguage: {
|
|
402
402
|
python: {
|
|
403
403
|
method: 'split.create',
|
|
@@ -454,9 +454,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
454
454
|
"status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing';",
|
|
455
455
|
],
|
|
456
456
|
response:
|
|
457
|
-
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }",
|
|
457
|
+
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }",
|
|
458
458
|
markdown:
|
|
459
|
-
"## list\n\n`client.split.list(created_at_on_or_after?: string, created_at_on_or_before?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n\n**get** `/api/v1/split/jobs`\n\nList document split jobs.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'`\n Filter by job status (pending, processing, completed, failed, cancelled)\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const splitListResponse of client.split.list()) {\n console.log(splitListResponse);\n}\n```",
|
|
459
|
+
"## list\n\n`client.split.list(created_at_on_or_after?: string, created_at_on_or_before?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: object[]; }`\n\n**get** `/api/v1/split/jobs`\n\nList document split jobs.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'`\n Filter by job status (pending, processing, completed, failed, cancelled)\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n - `warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const splitListResponse of client.split.list()) {\n console.log(splitListResponse);\n}\n```",
|
|
460
460
|
perLanguage: {
|
|
461
461
|
python: {
|
|
462
462
|
method: 'split.list',
|
|
@@ -503,9 +503,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
503
503
|
qualified: 'client.split.get',
|
|
504
504
|
params: ['split_job_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
505
505
|
response:
|
|
506
|
-
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }",
|
|
506
|
+
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }",
|
|
507
507
|
markdown:
|
|
508
|
-
"## get\n\n`client.split.get(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n\n**get** `/api/v1/split/jobs/{split_job_id}`\n\nGet a document split job.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.split.get('split_job_id');\n\nconsole.log(split);\n```",
|
|
508
|
+
"## get\n\n`client.split.get(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: object[]; }`\n\n**get** `/api/v1/split/jobs/{split_job_id}`\n\nGet a document split job.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n - `warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.split.get('split_job_id');\n\nconsole.log(split);\n```",
|
|
509
509
|
perLanguage: {
|
|
510
510
|
python: {
|
|
511
511
|
method: 'split.get',
|
|
@@ -602,9 +602,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
602
602
|
qualified: 'client.split.cancel',
|
|
603
603
|
params: ['split_job_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
604
604
|
response:
|
|
605
|
-
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }",
|
|
605
|
+
"{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }",
|
|
606
606
|
markdown:
|
|
607
|
-
"## cancel\n\n`client.split.cancel(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n\n**post** `/api/v1/split/jobs/{split_job_id}/cancel`\n\nCancel a running split job.\n\nRequests cancellation; the job transitions to CANCELLED asynchronously once processing stops. Returns the job, which may still be in its current non-terminal state. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; transaction_id?: string; updated_at?: string; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.split.cancel('split_job_id');\n\nconsole.log(response);\n```",
|
|
607
|
+
"## cancel\n\n`client.split.cancel(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: split_result_response; splitting_strategy?: object; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: object[]; }`\n\n**post** `/api/v1/split/jobs/{split_job_id}/cancel`\n\nCancel a running split job.\n\nRequests cancellation; the job transitions to CANCELLED asynchronously once processing stops. Returns the job, which may still be in its current non-terminal state. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input_type: 'file_id' | 'parse_job_id' | 'url'; file_input: string; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; parse_config_id?: string; parse_tier?: string; result?: { segments: split_segment_response[]; }; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; transaction_id?: string; updated_at?: string; warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]; }`\n A split job.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input_type: 'file_id' | 'parse_job_id' | 'url'`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_config_id?: string`\n - `parse_tier?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n - `target_pages?: string`\n - `transaction_id?: string`\n - `updated_at?: string`\n - `warnings?: { category_names: string[]; code: 'catch_all_category' | 'missing_description' | 'near_duplicate_description' | 'near_duplicate_name'; message: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.split.cancel('split_job_id');\n\nconsole.log(response);\n```",
|
|
608
608
|
perLanguage: {
|
|
609
609
|
python: {
|
|
610
610
|
method: 'split.cancel',
|
|
@@ -652,7 +652,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
652
652
|
qualified: 'client.parsing.create',
|
|
653
653
|
params: [
|
|
654
654
|
"tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | string;",
|
|
655
|
-
"version: 'latest' | '2026-
|
|
655
|
+
"version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string;",
|
|
656
656
|
'organization_id?: string;',
|
|
657
657
|
'project_id?: string;',
|
|
658
658
|
'agentic_options?: { custom_prompt?: string; };',
|
|
@@ -664,10 +664,10 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
664
664
|
'file_id?: string;',
|
|
665
665
|
'http_proxy?: string;',
|
|
666
666
|
'input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; };',
|
|
667
|
-
"output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; };",
|
|
667
|
+
"output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; };",
|
|
668
668
|
'page_ranges?: { max_pages?: number; target_pages?: string; };',
|
|
669
669
|
'processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; };',
|
|
670
|
-
"processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-
|
|
670
|
+
"processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; }; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; };",
|
|
671
671
|
'source_url?: string;',
|
|
672
672
|
'user_metadata?: object;',
|
|
673
673
|
'webhook_configuration_ids?: string[];',
|
|
@@ -676,7 +676,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
676
676
|
response:
|
|
677
677
|
"{ id: string; project_id: string; status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; usage?: { credits?: number; }; user_metadata?: object; }",
|
|
678
678
|
markdown:
|
|
679
|
-
"## create\n\n`client.parsing.create(tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | string, version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string, organization_id?: string, project_id?: string, agentic_options?: { custom_prompt?: string; }, client_name?: string, configuration_id?: string, crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }, disable_cache?: boolean, fast_options?: object, file_id?: string, http_proxy?: string, input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }, output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }, page_ranges?: { max_pages?: number; target_pages?: string; }, processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }, processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }, source_url?: string, user_metadata?: object, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; project_id: string; status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; usage?: object; user_metadata?: object; }`\n\n**post** `/api/v2/parse`\n\nParse a file by file ID or URL.\n\nProvide either `file_id` (a previously uploaded file) or\n`source_url` (a publicly accessible URL). Configure parsing\nwith options like `tier`, `target_pages`, and `lang`.\n\n## Tiers\n\n- `fast` — rule-based, cheapest, no AI\n- `cost_effective` — balanced speed and quality\n- `agentic` — full AI-powered parsing\n- `agentic_plus` — premium AI with specialized features\n\nThe job runs asynchronously. Poll `GET /parse/{job_id}` with\n`expand=text` or `expand=markdown` to retrieve results.\n\n### Parameters\n\n- `tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | string`\n Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy)\n\n- `version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string`\n Version for the selected tier. Use `latest`, or pin one of that tier's dated versions.\n\nCurrent `latest` by tier:\n- `fast`: `2026-06-15`\n- `cost_effective`: `2026-09-28`\n- `agentic`: `2026-10-16`\n- `agentic_plus`: `2026-09-28`\n\nFull list: `GET /api/v2/parse/versions`.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `agentic_options?: { custom_prompt?: string; }`\n Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus).\n\nThese options customize how the AI processes and interprets document content.\nOnly applicable when using non-fast tiers.\n - `custom_prompt?: string`\n Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: 'Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.'\n\n- `client_name?: string`\n Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2'\n\n- `configuration_id?: string`\n ID of a saved parse configuration. When set, `tier` and `version` default to the saved configuration's values — omit them or pass `'configured'`.\n\n- `crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }`\n Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges\n - `bottom?: number`\n Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded\n - `left?: number`\n Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded\n - `right?: number`\n Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded\n - `top?: number`\n Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded\n\n- `disable_cache?: boolean`\n Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results\n\n- `fast_options?: object`\n Options for fast tier parsing (rule-based, no AI).\n\nFast tier uses deterministic algorithms for text extraction without AI enhancement.\nIt's the fastest and most cost-effective option, best suited for simple documents\nwith standard layouts. Currently has no configurable options but reserved for\nfuture expansion.\n\n- `file_id?: string`\n ID of an existing file in the project to parse. Mutually exclusive with source_url\n\n- `http_proxy?: string`\n HTTP/HTTPS proxy for fetching source_url. Ignored if using file_id\n\n- `input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }`\n Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type\n - `html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }`\n HTML/web page parsing options (applies to .html, .htm files)\n - `image?: { camera_photo_correction?: boolean; }`\n Image parsing options (applies to .jpg, .jpeg, .png, .webp files)\n - `pdf?: object`\n PDF-specific parsing options (applies to .pdf files)\n - `presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }`\n Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)\n - `spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }`\n Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)\n\n- `output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }`\n Output formatting options for markdown, text, and extracted images\n - `additional_outputs?: string[]`\n Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: 'stripped_md' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. 'concatenated_stripped_txt' — all stripped pages concatenated into a single plain-text file with `\\n\\n---\\n\\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. 'word_bbox' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`.\n - `extract_printed_page_number?: boolean`\n Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers\n - `granular_bboxes?: 'cell' | 'line' | 'word'[]`\n Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape.\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n Image categories to save: 'screenshot' (full page renders), 'embedded' (images found within the document), 'layout' (cropped figures and diagrams). Defaults to saving 'layout' when the output links to cropped images; pass [] to save none\n - `markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }`\n Markdown formatting options including table styles and link annotations\n - `save_output_pdf?: boolean`\n Save a PDF copy of the parsed document, retrievable via `expand=output_pdf_content_metadata`. Not produced for spreadsheet, plain-text, or audio inputs\n - `spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }`\n Spatial text output options for preserving document layout structure\n - `tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }`\n Options for exporting tables as XLSX spreadsheets\n - `watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'`\n What to do with watermark text stamped across the page (e.g., 'CONFIDENTIAL', 'DRAFT'): 'move_to_end' (default) keeps it as the last block of the page's markdown, 'move_to_start' as the first block, and 'remove' drops it. The text output follows the same choice where the watermark is a line of its own in the PDF text layer. In every mode the detected text is reported in the page's `watermark` metadata. Requires version 2026-09-28 or later on the cost_effective, agentic, and agentic_plus tiers; ignored otherwise\n\n- `page_ranges?: { max_pages?: number; target_pages?: string; }`\n Page selection: limit total pages or specify exact pages to process\n - `max_pages?: number`\n Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence\n - `target_pages?: string`\n Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: '1,3,5' (pages 1, 3, 5), '1-5' (pages 1 through 5 inclusive), '1,3,5-8,10' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error\n\n- `processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }`\n Job execution controls including timeouts and failure thresholds\n - `job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }`\n Quality thresholds that determine when a job should fail vs complete with partial results\n - `timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }`\n Timeout settings for job execution. Increase for large or complex documents\n\n- `processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; }; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }`\n Document processing options including OCR, table extraction, and chart parsing\n - `aggressive_table_extraction?: boolean`\n Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables\n - `auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; }; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]`\n Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered\n - `confidence_score_effort?: 'high'`\n Confidence scoring effort. Omit for standard scoring. 'high': more accurate assessment of the parsing quality of every page, plus a document-level score in the result metadata; costs an additional 5 credits per page\n - `cost_optimizer?: { enable?: boolean; }`\n Cost optimizer configuration for reducing parsing costs on simpler pages.\n\nWhen enabled, the parser analyzes each page and routes simpler pages to faster,\ncheaper processing while preserving quality for complex pages. Only works with\n'agentic' or 'agentic_plus' tiers.\n - `disable_heuristics?: boolean`\n Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results\n - `forms?: 'default' | 'enrich'`\n Beta: set to 'enrich' to run an additional AI form-analysis pass on pages detected as forms, producing a structured tree of the form's sections, fields, and fillable grids. Retrieve the result with expand=forms. 'default' (the default) applies standard parsing with no extra pass. Not available on the fast tier\n - `ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }`\n Options for ignoring specific text types (diagonal, hidden, text in images)\n - `ocr_parameters?: { languages?: string[]; }`\n OCR configuration including language detection settings\n - `specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'`\n Enable AI-powered chart analysis. Modes: 'efficient' (fast, lower cost), 'agentic' (balanced), 'agentic_plus' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set\n\n- `source_url?: string`\n Public URL of the document to parse. Mutually exclusive with file_id\n\n- `user_metadata?: object`\n Arbitrary key/value tags to attach to this job. Returned when retrieving the job. Not searchable. Limits apply to the number of entries and the length of keys and values; oversized metadata is rejected.\n\n- `webhook_configuration_ids?: string[]`\n IDs of saved webhook configurations to notify for this job.\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services\n\n### Returns\n\n- `{ id: string; project_id: string; status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; usage?: { credits?: number; }; user_metadata?: object; }`\n A parse job.\n\n - `id: string`\n - `project_id: string`\n - `status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'`\n - `created_at?: string`\n - `error_message?: string`\n - `name?: string`\n - `tier?: string`\n - `updated_at?: string`\n - `usage?: { credits?: number; }`\n - `user_metadata?: object`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst parsing = await client.parsing.create({ tier: 'fast', version: 'latest' });\n\nconsole.log(parsing);\n```",
|
|
679
|
+
"## create\n\n`client.parsing.create(tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | string, version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string, organization_id?: string, project_id?: string, agentic_options?: { custom_prompt?: string; }, client_name?: string, configuration_id?: string, crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }, disable_cache?: boolean, fast_options?: object, file_id?: string, http_proxy?: string, input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }, output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }, page_ranges?: { max_pages?: number; target_pages?: string; }, processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }, processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }, source_url?: string, user_metadata?: object, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; project_id: string; status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; usage?: object; user_metadata?: object; }`\n\n**post** `/api/v2/parse`\n\nParse a file by file ID or URL.\n\nProvide either `file_id` (a previously uploaded file) or\n`source_url` (a publicly accessible URL). Configure parsing\nwith options like `tier`, `target_pages`, and `lang`.\n\n## Tiers\n\n- `fast` — rule-based, cheapest, no AI\n- `cost_effective` — balanced speed and quality\n- `agentic` — full AI-powered parsing\n- `agentic_plus` — premium AI with specialized features\n\nThe job runs asynchronously. Poll `GET /parse/{job_id}` with\n`expand=text` or `expand=markdown` to retrieve results.\n\n### Parameters\n\n- `tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus' | string`\n Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy)\n\n- `version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string`\n Version for the selected tier. Use `latest`, or pin one of that tier's dated versions.\n\nCurrent `latest` by tier:\n- `fast`: `2026-11-12`\n- `cost_effective`: `2026-11-09`\n- `agentic`: `2026-11-09`\n- `agentic_plus`: `2026-11-19`\n\nFull list: `GET /api/v2/parse/versions`.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `agentic_options?: { custom_prompt?: string; }`\n Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus).\n\nThese options customize how the AI processes and interprets document content.\nOnly applicable when using non-fast tiers.\n - `custom_prompt?: string`\n Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: 'Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.'\n\n- `client_name?: string`\n Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2'\n\n- `configuration_id?: string`\n ID of a saved parse configuration. When set, `tier` and `version` default to the saved configuration's values — omit them or pass `'configured'`.\n\n- `crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }`\n Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges\n - `bottom?: number`\n Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded\n - `left?: number`\n Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded\n - `right?: number`\n Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded\n - `top?: number`\n Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded\n\n- `disable_cache?: boolean`\n Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results\n\n- `fast_options?: object`\n Options for fast tier parsing (rule-based, no AI).\n\nFast tier uses deterministic algorithms for text extraction without AI enhancement.\nIt's the fastest and most cost-effective option, best suited for simple documents\nwith standard layouts. Currently has no configurable options but reserved for\nfuture expansion.\n\n- `file_id?: string`\n ID of an existing file in the project to parse. Mutually exclusive with source_url\n\n- `http_proxy?: string`\n HTTP/HTTPS proxy for fetching source_url. Ignored if using file_id\n\n- `input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }`\n Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type\n - `html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }`\n HTML/web page parsing options (applies to .html, .htm files)\n - `image?: { camera_photo_correction?: boolean; }`\n Image parsing options (applies to .jpg, .jpeg, .png, .webp files)\n - `pdf?: object`\n PDF-specific parsing options (applies to .pdf files)\n - `presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }`\n Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)\n - `spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }`\n Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)\n\n- `output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }`\n Output formatting options for markdown, text, and extracted images\n - `additional_outputs?: string[]`\n Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: 'stripped_md' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. 'concatenated_stripped_txt' — all stripped pages concatenated into a single plain-text file with `\\n\\n---\\n\\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. 'word_bbox' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`.\n - `extract_printed_page_number?: boolean`\n Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers\n - `granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]`\n Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell; 'char' adds one box per character inside each grounded word (`chars` on each word), available on the `agentic_plus` tier only. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape.\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n Image categories to save: 'screenshot' (full page renders), 'embedded' (images found within the document), 'layout' (cropped figures and diagrams). Defaults to saving 'layout' when the output links to cropped images; pass [] to save none\n - `markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: boolean; }; }`\n Markdown formatting options including table styles and link annotations\n - `save_output_pdf?: boolean`\n Save a PDF copy of the parsed document, retrievable via `expand=output_pdf_content_metadata`. Not produced for spreadsheet, plain-text, or audio inputs\n - `spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }`\n Spatial text output options for preserving document layout structure\n - `tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }`\n Options for exporting tables as XLSX spreadsheets\n - `watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'`\n What to do with watermark text stamped across the page (e.g., 'CONFIDENTIAL', 'DRAFT'): 'move_to_end' (default) keeps it as the last block of the page's markdown, 'move_to_start' as the first block, and 'remove' drops it. The text output follows the same choice where the watermark is a line of its own in the PDF text layer. In every mode the detected text is reported in the page's `watermark` metadata. Requires version 2026-09-28 or later on the cost_effective, agentic, and agentic_plus tiers; ignored otherwise\n\n- `page_ranges?: { max_pages?: number; target_pages?: string; }`\n Page selection: limit total pages or specify exact pages to process\n - `max_pages?: number`\n Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence\n - `target_pages?: string`\n Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: '1,3,5' (pages 1, 3, 5), '1-5' (pages 1 through 5 inclusive), '1,3,5-8,10' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error\n\n- `processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }`\n Job execution controls including timeouts and failure thresholds\n - `job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }`\n Quality thresholds that determine when a job should fail vs complete with partial results\n - `timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }`\n Timeout settings for job execution. Increase for large or complex documents\n\n- `processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; }; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }`\n Document processing options including OCR, table extraction, and chart parsing\n - `aggressive_table_extraction?: boolean`\n Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables\n - `auto_mode_configuration?: { parsing_conf: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; custom_prompt?: string; extract_layout?: boolean; high_res_ocr?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; }; language?: string; outlined_table_extraction?: boolean; presentation?: { out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version?: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; }; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]`\n Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered\n - `confidence_score_effort?: 'high'`\n Confidence scoring effort. Omit for standard scoring. 'high': more accurate assessment of the parsing quality of every page, plus a document-level score in the result metadata; costs an additional 5 credits per page\n - `cost_optimizer?: { enable?: boolean; }`\n Cost optimizer configuration for reducing parsing costs on simpler pages.\n\nWhen enabled, the parser analyzes each page and routes simpler pages to faster,\ncheaper processing while preserving quality for complex pages. Only works with\n'agentic' or 'agentic_plus' tiers.\n - `disable_heuristics?: boolean`\n Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results\n - `forms?: 'default' | 'enrich'`\n Beta: set to 'enrich' to run an additional AI form-analysis pass on pages detected as forms, producing a structured tree of the form's sections, fields, and fillable grids. Retrieve the result with expand=forms. 'default' (the default) applies standard parsing with no extra pass. Not available on the fast tier\n - `ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }`\n Options for ignoring specific text types (diagonal, hidden, text in images)\n - `ocr_parameters?: { languages?: string[]; }`\n OCR configuration including language detection settings\n - `specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'`\n Enable AI-powered chart analysis. Modes: 'efficient' (fast, lower cost), 'agentic' (balanced), 'agentic_plus' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set\n\n- `source_url?: string`\n Public URL of the document to parse. Mutually exclusive with file_id\n\n- `user_metadata?: object`\n Arbitrary key/value tags to attach to this job. Returned when retrieving the job. Not searchable. Limits apply to the number of entries and the length of keys and values; oversized metadata is rejected.\n\n- `webhook_configuration_ids?: string[]`\n IDs of saved webhook configurations to notify for this job.\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Webhook endpoints for job notifications. Maximum 10 total, including webhook_configuration_ids.\n\n### Returns\n\n- `{ id: string; project_id: string; status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; usage?: { credits?: number; }; user_metadata?: object; }`\n A parse job.\n\n - `id: string`\n - `project_id: string`\n - `status: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING'`\n - `created_at?: string`\n - `error_message?: string`\n - `name?: string`\n - `tier?: string`\n - `updated_at?: string`\n - `usage?: { credits?: number; }`\n - `user_metadata?: object`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst parsing = await client.parsing.create({ tier: 'fast', version: 'latest' });\n\nconsole.log(parsing);\n```",
|
|
680
680
|
perLanguage: {
|
|
681
681
|
python: {
|
|
682
682
|
method: 'parsing.create',
|
|
@@ -936,9 +936,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
936
936
|
stainlessPath: '(resource) parsing > (method) list_versions',
|
|
937
937
|
qualified: 'client.parsing.listVersions',
|
|
938
938
|
response:
|
|
939
|
-
"{ agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-06-15' | '2025-12-11'[]; latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }; }",
|
|
939
|
+
"{ agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-11-12' | '2026-06-15' | '2025-12-11'[]; latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }; }",
|
|
940
940
|
markdown:
|
|
941
|
-
"## list_versions\n\n`client.parsing.listVersions(): { agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-06-15' | '2025-12-11'[]; latest: object; }`\n\n**get** `/api/v2/parse/versions`\n\nList the parse versions accepted by each tier and what `latest` resolves to.\n\n### Returns\n\n- `{ agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-06-15' | '2025-12-11'[]; latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }; }`\n Versions accepted by the parse API, grouped by tier.\n\n - `agentic: string[]`\n - `agentic_plus: string[]`\n - `cost_effective: string[]`\n - `fast: '2026-06-15' | '2025-12-11'[]`\n - `latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.parsing.listVersions();\n\nconsole.log(response);\n```",
|
|
941
|
+
"## list_versions\n\n`client.parsing.listVersions(): { agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-11-12' | '2026-06-15' | '2025-12-11'[]; latest: object; }`\n\n**get** `/api/v2/parse/versions`\n\nList the parse versions accepted by each tier and what `latest` resolves to.\n\n### Returns\n\n- `{ agentic: string[]; agentic_plus: string[]; cost_effective: string[]; fast: '2026-11-12' | '2026-06-15' | '2025-12-11'[]; latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }; }`\n Versions accepted by the parse API, grouped by tier.\n\n - `agentic: string[]`\n - `agentic_plus: string[]`\n - `cost_effective: string[]`\n - `fast: '2026-11-12' | '2026-06-15' | '2025-12-11'[]`\n - `latest: { agentic: string; agentic_plus: string; cost_effective: string; fast: string; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst response = await client.parsing.listVersions();\n\nconsole.log(response);\n```",
|
|
942
942
|
perLanguage: {
|
|
943
943
|
python: {
|
|
944
944
|
method: 'parsing.list_versions',
|
|
@@ -988,15 +988,15 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
988
988
|
'file_input: string;',
|
|
989
989
|
'organization_id?: string;',
|
|
990
990
|
'project_id?: string;',
|
|
991
|
-
"configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; };",
|
|
991
|
+
"configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; };",
|
|
992
992
|
'configuration_id?: string;',
|
|
993
993
|
'webhook_configuration_ids?: string[];',
|
|
994
994
|
'webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[];',
|
|
995
995
|
],
|
|
996
996
|
response:
|
|
997
|
-
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
997
|
+
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
998
998
|
markdown:
|
|
999
|
-
"## create\n\n`client.extract.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }, configuration_id?: string, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**post** `/api/v2/extract`\n\nCreate an extraction job.\n\nExtracts structured data from a document using either a saved\nconfiguration or an inline JSON Schema.\n\n## Input\n\nProvide exactly one of:\n- `configuration_id` — reference a saved extraction config\n- `configuration` — inline configuration with a `data_schema`\n\n## Document input\n\nSet `file_input` to a file ID (`dfl-...`) or a\ncompleted parse job ID (`pjb-...`).\n\nThe job runs asynchronously. Poll `GET /extract/{job_id}` or\nregister a webhook to monitor completion.\n\n### Parameters\n\n- `file_input: string`\n File ID or parse job ID to extract from\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n Extract configuration combining parse and extract settings.\n - `data_schema: object`\n JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.\n - `advanced_citations?: boolean`\n More precise citation bounding boxes. Set to false for faster extraction with less precise boxes.\n - `cite_sources?: boolean`\n Include citations in results. Returned under `extract_metadata` (auto-included when set). Text-level on `turbo` (no bounding boxes).\n - `confidence_scores?: boolean`\n Include confidence scores in results. Returned under `extract_metadata` (auto-included when set).\n - `disable_cache?: boolean`\n Disable reuse and storage of Extract results\n - `extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'`\n Deprecated. Applies only to Agentic and Cost Effective versions 2.0 or earlier. Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row. Agentic Plus supports per_doc only.\n - `max_pages?: number`\n Maximum number of pages to process. Omit for no limit.\n - `parse_config_id?: string`\n Saved parse configuration ID to control how the document is parsed before extraction. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.\n - `parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'`\n Parse tier to use before extraction. Defaults to the extract tier if not specified. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.\n - `sheet_names?: string[]`\n Optional worksheet names to extract when spreadsheet_mode is on. Overrides target_pages for spreadsheets; omit to extract every sheet. Names are matched exactly (case-sensitive) — pass them as a list, e.g. [\"Sheet 1\", \"My Sheet\"].\n - `spreadsheet_mode?: boolean`\n
|
|
999
|
+
"## create\n\n`client.extract.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }, configuration_id?: string, webhook_configuration_ids?: string[], webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**post** `/api/v2/extract`\n\nCreate an extraction job.\n\nExtracts structured data from a document using either a saved\nconfiguration or an inline JSON Schema.\n\n## Input\n\nProvide exactly one of:\n- `configuration_id` — reference a saved extraction config\n- `configuration` — inline configuration with a `data_schema`\n\n## Document input\n\nSet `file_input` to a file ID (`dfl-...`) or a\ncompleted parse job ID (`pjb-...`).\n\nThe job runs asynchronously. Poll `GET /extract/{job_id}` or\nregister a webhook to monitor completion.\n\n### Parameters\n\n- `file_input: string`\n File ID or parse job ID to extract from\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n Extract configuration combining parse and extract settings.\n - `data_schema: object`\n JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.\n - `advanced_citations?: boolean`\n More precise citation bounding boxes. Set to false for faster extraction with less precise boxes.\n - `cite_sources?: boolean`\n Include citations in results. Returned under `extract_metadata` (auto-included when set). Text-level on `turbo` (no bounding boxes).\n - `confidence_scores?: boolean`\n Include confidence scores in results. Returned under `extract_metadata` (auto-included when set).\n - `disable_cache?: boolean`\n Disable reuse and storage of Extract results\n - `effort?: 'max'`\n Use 'max' for additional processing effort on agentic_plus. Priced by the processing each document needs, with the page price as the minimum. Omit or set to null for the tier's default behavior.\n - `extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'`\n Deprecated. Applies only to Agentic and Cost Effective versions 2.0 or earlier. Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row. Agentic Plus supports per_doc only.\n - `max_pages?: number`\n Maximum number of pages to process. Omit for no limit.\n - `parse_config_id?: string`\n Saved parse configuration ID to control how the document is parsed before extraction. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.\n - `parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'`\n Parse tier to use before extraction. Defaults to the extract tier if not specified. Turbo extract does not support parse configuration or produce a parse output; use another tier if your workflow requires parsed text.\n - `sheet_names?: string[]`\n Optional worksheet names to extract when spreadsheet_mode is on. Overrides target_pages for spreadsheets; omit to extract every sheet. Names are matched exactly (case-sensitive) — pass them as a list, e.g. [\"Sheet 1\", \"My Sheet\"].\n - `spreadsheet_mode?: boolean`\n Extract structured data directly from spreadsheet cells (.xlsx/.xls/.csv). Billed at the standard per-page Extract rate, with page count derived from workbook size.\n - `system_prompt?: string`\n Custom system prompt to guide extraction behavior\n - `target_pages?: string`\n Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.\n - `tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'`\n Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), agentic_plus (50 credits/page), or turbo (35 credits/page)\n - `version?: string`\n Extract version name, such as '2.5'. Use 'latest' for the newest compatible release for the selected tier. Dates (YYYY-MM-DD) are also supported, which will use the latest version on or before the specified date.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `webhook_configuration_ids?: string[]`\n IDs of saved webhook configurations to notify for this job.\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractV2Job = await client.extract.create({ file_input: 'dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee' });\n\nconsole.log(extractV2Job);\n```",
|
|
1000
1000
|
perLanguage: {
|
|
1001
1001
|
python: {
|
|
1002
1002
|
method: 'extract.create',
|
|
@@ -1040,7 +1040,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1040
1040
|
httpMethod: 'get',
|
|
1041
1041
|
summary: 'List Extract Jobs',
|
|
1042
1042
|
description:
|
|
1043
|
-
'List extraction jobs with optional filtering and pagination.\n\nFilter by `configuration_id`, `status`, `file_input`,\nor creation date range. Results are returned newest-first.\nUse `expand=configuration` to include the full configuration used,\nand `expand=extract_metadata` for per-field metadata.',
|
|
1043
|
+
'List extraction jobs with optional filtering and pagination.\n\nFilter by `configuration_id`, `status`, `file_input`, `review_status`,\nor creation date range. Results are returned newest-first.\n`review_status=pending` lists completed jobs waiting for review,\nunless `status` names another. A review stays pending when its job\nfails or is cancelled, so pass that `status` to list those.\nUse `expand=configuration` to include the full configuration used,\nand `expand=extract_metadata` for per-field metadata.',
|
|
1044
1044
|
stainlessPath: '(resource) extract > (method) list',
|
|
1045
1045
|
qualified: 'client.extract.list',
|
|
1046
1046
|
params: [
|
|
@@ -1056,12 +1056,13 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1056
1056
|
'page_size?: number;',
|
|
1057
1057
|
'page_token?: string;',
|
|
1058
1058
|
'project_id?: string;',
|
|
1059
|
+
"review_status?: 'approved' | 'none' | 'pending' | 'rejected';",
|
|
1059
1060
|
"status?: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING' | 'THROTTLED';",
|
|
1060
1061
|
],
|
|
1061
1062
|
response:
|
|
1062
|
-
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1063
|
+
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1063
1064
|
markdown:
|
|
1064
|
-
"## list\n\n`client.extract.list(configuration_id?: string, created_at_on_or_after?: string, created_at_on_or_before?: string, document_input_type?: string, document_input_value?: string, expand?: string[], file_input?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING' | 'THROTTLED'): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**get** `/api/v2/extract`\n\nList extraction jobs with optional filtering and pagination.\n\nFilter by `configuration_id`, `status`, `file_input`,\nor creation date range. Results are returned newest-first.\nUse `expand=configuration` to include the full configuration used,\nand `expand=extract_metadata` for per-field metadata.\n\n### Parameters\n\n- `configuration_id?: string`\n Filter by configuration ID\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `document_input_type?: string`\n Filter by document input type (file_id or parse_job_id)\n\n- `document_input_value?: string`\n Deprecated: use file_input instead\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata\n\n- `file_input?: string`\n Filter by file input value\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n Number of items per page\n\n- `page_token?: string`\n Token for pagination\n\n- `project_id?: string`\n\n- `status?: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING' | 'THROTTLED'`\n Filter by status\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const extractV2Job of client.extract.list()) {\n console.log(extractV2Job);\n}\n```",
|
|
1065
|
+
"## list\n\n`client.extract.list(configuration_id?: string, created_at_on_or_after?: string, created_at_on_or_before?: string, document_input_type?: string, document_input_value?: string, expand?: string[], file_input?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, review_status?: 'approved' | 'none' | 'pending' | 'rejected', status?: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING' | 'THROTTLED'): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**get** `/api/v2/extract`\n\nList extraction jobs with optional filtering and pagination.\n\nFilter by `configuration_id`, `status`, `file_input`, `review_status`,\nor creation date range. Results are returned newest-first.\n`review_status=pending` lists completed jobs waiting for review,\nunless `status` names another. A review stays pending when its job\nfails or is cancelled, so pass that `status` to list those.\nUse `expand=configuration` to include the full configuration used,\nand `expand=extract_metadata` for per-field metadata.\n\n### Parameters\n\n- `configuration_id?: string`\n Filter by configuration ID\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `document_input_type?: string`\n Filter by document input type (file_id or parse_job_id)\n\n- `document_input_value?: string`\n Deprecated: use file_input instead\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata\n\n- `file_input?: string`\n Filter by file input value\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n Number of items per page\n\n- `page_token?: string`\n Token for pagination\n\n- `project_id?: string`\n\n- `review_status?: 'approved' | 'none' | 'pending' | 'rejected'`\n Filter by review status; none is a job without a review\n\n- `status?: 'CANCELLED' | 'COMPLETED' | 'FAILED' | 'PENDING' | 'RUNNING' | 'THROTTLED'`\n Filter by status\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const extractV2Job of client.extract.list()) {\n console.log(extractV2Job);\n}\n```",
|
|
1065
1066
|
perLanguage: {
|
|
1066
1067
|
python: {
|
|
1067
1068
|
method: 'extract.list',
|
|
@@ -1109,9 +1110,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1109
1110
|
qualified: 'client.extract.get',
|
|
1110
1111
|
params: ['job_id: string;', 'expand?: string[];', 'organization_id?: string;', 'project_id?: string;'],
|
|
1111
1112
|
response:
|
|
1112
|
-
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1113
|
+
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1113
1114
|
markdown:
|
|
1114
|
-
"## get\n\n`client.extract.get(job_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**get** `/api/v2/extract/{job_id}`\n\nGet a single extraction job by ID.\n\nReturns the job status and results when complete.\nUse `expand=configuration` to include the full configuration used,\n`expand=extract_metadata` for per-field metadata, and\n`expand=usage` for credits billed against the job.\n\n### Parameters\n\n- `job_id: string`\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata, usage\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractV2Job = await client.extract.get('job_id');\n\nconsole.log(extractV2Job);\n```",
|
|
1115
|
+
"## get\n\n`client.extract.get(job_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**get** `/api/v2/extract/{job_id}`\n\nGet a single extraction job by ID.\n\nReturns the job status and results when complete.\nUse `expand=configuration` to include the full configuration used,\n`expand=extract_metadata` for per-field metadata, and\n`expand=usage` for credits billed against the job.\n\n### Parameters\n\n- `job_id: string`\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata, usage\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractV2Job = await client.extract.get('job_id');\n\nconsole.log(extractV2Job);\n```",
|
|
1115
1116
|
perLanguage: {
|
|
1116
1117
|
python: {
|
|
1117
1118
|
method: 'extract.get',
|
|
@@ -1208,9 +1209,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1208
1209
|
qualified: 'client.extract.cancel',
|
|
1209
1210
|
params: ['job_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
1210
1211
|
response:
|
|
1211
|
-
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1212
|
+
"{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }",
|
|
1212
1213
|
markdown:
|
|
1213
|
-
"## cancel\n\n`client.extract.cancel(job_id: string, organization_id?: string, project_id?: string): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**post** `/api/v2/extract/{job_id}/cancel`\n\nCancel a running extraction job.\n\nStops processing and marks the job as CANCELLED. Returns the updated job. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.\n\n### Parameters\n\n- `job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractV2Job = await client.extract.cancel('job_id');\n\nconsole.log(extractV2Job);\n```",
|
|
1214
|
+
"## cancel\n\n`client.extract.cancel(job_id: string, organization_id?: string, project_id?: string): { id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: extract_configuration; configuration_id?: string; error_message?: string; extract_metadata?: extract_job_metadata; extract_result?: object | object[]; metadata?: object; usage?: object; }`\n\n**post** `/api/v2/extract/{job_id}/cancel`\n\nCancel a running extraction job.\n\nStops processing and marks the job as CANCELLED. Returns the updated job. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.\n\n### Parameters\n\n- `job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }; configuration_id?: string; error_message?: string; extract_metadata?: { field_metadata?: extracted_field_metadata; parse_job_id?: string; parse_tier?: string; }; extract_result?: object | object[]; metadata?: { usage?: object; }; usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }; }`\n An extraction job.\n\n - `id: string`\n - `created_at: string`\n - `file_input: string`\n - `project_id: string`\n - `status: string`\n - `updated_at: string`\n - `configuration?: { data_schema: object; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; }`\n - `configuration_id?: string`\n - `error_message?: string`\n - `extract_metadata?: { field_metadata?: { document_metadata?: object; page_metadata?: object[]; row_metadata?: object[]; }; parse_job_id?: string; parse_tier?: string; }`\n - `extract_result?: object | object[]`\n - `metadata?: { usage?: { num_pages_billed?: number; num_pages_extracted?: number; }; }`\n - `usage?: { credits?: number; extract_credits?: number; parse_credits?: number; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractV2Job = await client.extract.cancel('job_id');\n\nconsole.log(extractV2Job);\n```",
|
|
1214
1215
|
perLanguage: {
|
|
1215
1216
|
python: {
|
|
1216
1217
|
method: 'extract.cancel',
|
|
@@ -1315,7 +1316,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1315
1316
|
response:
|
|
1316
1317
|
"{ name: string; parameters: object | object | object | object | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | object; }",
|
|
1317
1318
|
markdown:
|
|
1318
|
-
"## generate_schema\n\n`client.extract.generateSchema(organization_id?: string, project_id?: string, data_schema?: object, file_id?: string, name?: string, prompt?: string): { name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; }`\n\n**post** `/api/v2/extract/schema/generate`\n\nGenerate a JSON schema and return a product configuration request.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_schema?: object`\n Optional schema to validate, refine, or extend\n\n- `file_id?: string`\n Optional file ID to analyze for schema generation\n\n- `name?: string`\n Name for the generated configuration (auto-generated if omitted)\n\n- `prompt?: string`\n Natural language description of the data structure to extract\n\n### Returns\n\n- `{ name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-
|
|
1319
|
+
"## generate_schema\n\n`client.extract.generateSchema(organization_id?: string, project_id?: string, data_schema?: object, file_id?: string, name?: string, prompt?: string): { name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; }`\n\n**post** `/api/v2/extract/schema/generate`\n\nGenerate a JSON schema and return a product configuration request.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_schema?: object`\n Optional schema to validate, refine, or extend\n\n- `file_id?: string`\n Optional file ID to analyze for schema generation\n\n- `name?: string`\n Name for the generated configuration (auto-generated if omitted)\n\n- `prompt?: string`\n Natural language description of the data structure to extract\n\n### Returns\n\n- `{ name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; }`\n Request body for creating a product configuration.\n\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationCreate = await client.extract.generateSchema();\n\nconsole.log(configurationCreate);\n```",
|
|
1319
1320
|
perLanguage: {
|
|
1320
1321
|
python: {
|
|
1321
1322
|
method: 'extract.generate_schema',
|
|
@@ -1352,6 +1353,391 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1352
1353
|
},
|
|
1353
1354
|
},
|
|
1354
1355
|
},
|
|
1356
|
+
{
|
|
1357
|
+
name: 'create',
|
|
1358
|
+
endpoint: '/api/v2/extract/{job_id}/review',
|
|
1359
|
+
httpMethod: 'post',
|
|
1360
|
+
summary: 'Create Extract Review',
|
|
1361
|
+
description:
|
|
1362
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nTurn review on for an extract job.\n\nFields read below `confidence_threshold`, and required fields left empty, are\nflagged for a person to check. Every setting has a default, so the body can be\nleft out. A job still running can be named: it waits for review once it\ncompletes. A job that failed or was cancelled without a review, or that cannot\nbe reviewed, answers 409 with `code: job_not_reviewable`; a field in\n`fields_in_scope` the job's schema does not have answers 400.\n\nAnswers 201 with the new review, or 200 with the job's existing review, whose\nsettings stay as they are.",
|
|
1363
|
+
stainlessPath: '(resource) extract.review > (method) create',
|
|
1364
|
+
qualified: 'client.extract.review.create',
|
|
1365
|
+
params: [
|
|
1366
|
+
'job_id: string;',
|
|
1367
|
+
'organization_id?: string;',
|
|
1368
|
+
'project_id?: string;',
|
|
1369
|
+
'confidence_threshold?: number;',
|
|
1370
|
+
'fields_in_scope?: string[];',
|
|
1371
|
+
'required_fields?: string[];',
|
|
1372
|
+
],
|
|
1373
|
+
response:
|
|
1374
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1375
|
+
markdown:
|
|
1376
|
+
"## create\n\n`client.extract.review.create(job_id: string, organization_id?: string, project_id?: string, confidence_threshold?: number, fields_in_scope?: string[], required_fields?: string[]): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**post** `/api/v2/extract/{job_id}/review`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nTurn review on for an extract job.\n\nFields read below `confidence_threshold`, and required fields left empty, are\nflagged for a person to check. Every setting has a default, so the body can be\nleft out. A job still running can be named: it waits for review once it\ncompletes. A job that failed or was cancelled without a review, or that cannot\nbe reviewed, answers 409 with `code: job_not_reviewable`; a field in\n`fields_in_scope` the job's schema does not have answers 400.\n\nAnswers 201 with the new review, or 200 with the job's existing review, whose\nsettings stay as they are.\n\n### Parameters\n\n- `job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `confidence_threshold?: number`\n Fields read below this confidence are flagged.\n\n- `fields_in_scope?: string[]`\n JSON Pointers of the fields the threshold applies to; empty means all.\n\n- `required_fields?: string[]`\n JSON Pointers of fields flagged when empty; defaults to the schema's required.\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.create('job_id');\n\nconsole.log(extractReview);\n```",
|
|
1377
|
+
perLanguage: {
|
|
1378
|
+
python: {
|
|
1379
|
+
method: 'extract.review.create',
|
|
1380
|
+
example:
|
|
1381
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.create(\n job_id="job_id",\n)\nprint(extract_review.id)',
|
|
1382
|
+
},
|
|
1383
|
+
go: {
|
|
1384
|
+
method: 'client.Extract.Review.New',
|
|
1385
|
+
example:
|
|
1386
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.New(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewNewParams{},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1387
|
+
},
|
|
1388
|
+
java: {
|
|
1389
|
+
method: 'extract().review().create',
|
|
1390
|
+
example:
|
|
1391
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewCreateParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ExtractReview extractReview = client.extract().review().create("job_id");\n }\n}',
|
|
1392
|
+
},
|
|
1393
|
+
csharp: {
|
|
1394
|
+
method: 'Extract.Review.Create',
|
|
1395
|
+
example:
|
|
1396
|
+
'ReviewCreateParams parameters = new() { JobID = "job_id" };\n\nvar extractReview = await client.Extract.Review.Create(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1397
|
+
},
|
|
1398
|
+
typescript: {
|
|
1399
|
+
method: 'client.extract.review.create',
|
|
1400
|
+
example:
|
|
1401
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.create('job_id');\n\nconsole.log(extractReview.id);",
|
|
1402
|
+
},
|
|
1403
|
+
http: {
|
|
1404
|
+
example:
|
|
1405
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review \\\n -X POST \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"',
|
|
1406
|
+
},
|
|
1407
|
+
cli: {
|
|
1408
|
+
method: 'review create',
|
|
1409
|
+
example: "llp extract:review create \\\n --api-key 'My API Key' \\\n --job-id job_id",
|
|
1410
|
+
},
|
|
1411
|
+
},
|
|
1412
|
+
},
|
|
1413
|
+
{
|
|
1414
|
+
name: 'get',
|
|
1415
|
+
endpoint: '/api/v2/extract/{job_id}/review',
|
|
1416
|
+
httpMethod: 'get',
|
|
1417
|
+
summary: 'Get Extract Review',
|
|
1418
|
+
description:
|
|
1419
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nGet an extract job's review: its flags, field actions and decision, with the\nresult as the model read it and as reviewed. A job without a review answers 404.",
|
|
1420
|
+
stainlessPath: '(resource) extract.review > (method) get',
|
|
1421
|
+
qualified: 'client.extract.review.get',
|
|
1422
|
+
params: ['job_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
1423
|
+
response:
|
|
1424
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1425
|
+
markdown:
|
|
1426
|
+
"## get\n\n`client.extract.review.get(job_id: string, organization_id?: string, project_id?: string): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**get** `/api/v2/extract/{job_id}/review`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nGet an extract job's review: its flags, field actions and decision, with the\nresult as the model read it and as reviewed. A job without a review answers 404.\n\n### Parameters\n\n- `job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.get('job_id');\n\nconsole.log(extractReview);\n```",
|
|
1427
|
+
perLanguage: {
|
|
1428
|
+
python: {
|
|
1429
|
+
method: 'extract.review.get',
|
|
1430
|
+
example:
|
|
1431
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.get(\n job_id="job_id",\n)\nprint(extract_review.id)',
|
|
1432
|
+
},
|
|
1433
|
+
go: {
|
|
1434
|
+
method: 'client.Extract.Review.Get',
|
|
1435
|
+
example:
|
|
1436
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.Get(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewGetParams{},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1437
|
+
},
|
|
1438
|
+
java: {
|
|
1439
|
+
method: 'extract().review().get',
|
|
1440
|
+
example:
|
|
1441
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewGetParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ExtractReview extractReview = client.extract().review().get("job_id");\n }\n}',
|
|
1442
|
+
},
|
|
1443
|
+
csharp: {
|
|
1444
|
+
method: 'Extract.Review.Get',
|
|
1445
|
+
example:
|
|
1446
|
+
'ReviewGetParams parameters = new() { JobID = "job_id" };\n\nvar extractReview = await client.Extract.Review.Get(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1447
|
+
},
|
|
1448
|
+
typescript: {
|
|
1449
|
+
method: 'client.extract.review.get',
|
|
1450
|
+
example:
|
|
1451
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.get('job_id');\n\nconsole.log(extractReview.id);",
|
|
1452
|
+
},
|
|
1453
|
+
http: {
|
|
1454
|
+
example:
|
|
1455
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"',
|
|
1456
|
+
},
|
|
1457
|
+
cli: {
|
|
1458
|
+
method: 'review get',
|
|
1459
|
+
example: "llp extract:review get \\\n --api-key 'My API Key' \\\n --job-id job_id",
|
|
1460
|
+
},
|
|
1461
|
+
},
|
|
1462
|
+
},
|
|
1463
|
+
{
|
|
1464
|
+
name: 'change_fields',
|
|
1465
|
+
endpoint: '/api/v2/extract/{job_id}/review/fields',
|
|
1466
|
+
httpMethod: 'post',
|
|
1467
|
+
summary: 'Change Extract Review Fields',
|
|
1468
|
+
description:
|
|
1469
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nConfirm, correct, clear, restore or undo fields of a completed job.\n\nThe changes apply in order, in one write. A job without a review gets one with\nthe default settings, at revision 0. A path that is not a field of the job, or a\nvalue the field's schema refuses, answers 400 and changes nothing.\nA job that has not completed answers 409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.",
|
|
1470
|
+
stainlessPath: '(resource) extract.review > (method) change_fields',
|
|
1471
|
+
qualified: 'client.extract.review.changeFields',
|
|
1472
|
+
params: [
|
|
1473
|
+
'job_id: string;',
|
|
1474
|
+
"changes: { change: 'clear' | 'confirm' | 'correct' | 'restore' | 'undo'; path: string; value?: object; }[];",
|
|
1475
|
+
'revision: number;',
|
|
1476
|
+
'organization_id?: string;',
|
|
1477
|
+
'project_id?: string;',
|
|
1478
|
+
],
|
|
1479
|
+
response:
|
|
1480
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1481
|
+
markdown:
|
|
1482
|
+
"## change_fields\n\n`client.extract.review.changeFields(job_id: string, changes: { change: 'clear' | 'confirm' | 'correct' | 'restore' | 'undo'; path: string; value?: object; }[], revision: number, organization_id?: string, project_id?: string): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**post** `/api/v2/extract/{job_id}/review/fields`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nConfirm, correct, clear, restore or undo fields of a completed job.\n\nThe changes apply in order, in one write. A job without a review gets one with\nthe default settings, at revision 0. A path that is not a field of the job, or a\nvalue the field's schema refuses, answers 400 and changes nothing.\nA job that has not completed answers 409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.\n\n### Parameters\n\n- `job_id: string`\n\n- `changes: { change: 'clear' | 'confirm' | 'correct' | 'restore' | 'undo'; path: string; value?: object; }[]`\n Changes to apply, in order.\n\n- `revision: number`\n The review's revision as the caller last read it.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.changeFields('job_id', { changes: [{ change: 'correct', path: '/total' }], revision: 0 });\n\nconsole.log(extractReview);\n```",
|
|
1483
|
+
perLanguage: {
|
|
1484
|
+
python: {
|
|
1485
|
+
method: 'extract.review.change_fields',
|
|
1486
|
+
example:
|
|
1487
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.change_fields(\n job_id="job_id",\n changes=[{\n "change": "correct",\n "path": "/total",\n }],\n revision=0,\n)\nprint(extract_review.id)',
|
|
1488
|
+
},
|
|
1489
|
+
go: {
|
|
1490
|
+
method: 'client.Extract.Review.ChangeFields',
|
|
1491
|
+
example:
|
|
1492
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.ChangeFields(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewChangeFieldsParams{\n\t\t\tChanges: []llamacloud.ExtractReviewChangeFieldsParamsChange{{\n\t\t\t\tChange: "correct",\n\t\t\t\tPath: "/total",\n\t\t\t}},\n\t\t\tRevision: 0,\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1493
|
+
},
|
|
1494
|
+
java: {
|
|
1495
|
+
method: 'extract().review().changeFields',
|
|
1496
|
+
example:
|
|
1497
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewChangeFieldsParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ReviewChangeFieldsParams params = ReviewChangeFieldsParams.builder()\n .jobId("job_id")\n .addChange(ReviewChangeFieldsParams.Change.builder()\n .change(ReviewChangeFieldsParams.Change.InnerChange.CORRECT)\n .path("/total")\n .build())\n .revision(0L)\n .build();\n ExtractReview extractReview = client.extract().review().changeFields(params);\n }\n}',
|
|
1498
|
+
},
|
|
1499
|
+
csharp: {
|
|
1500
|
+
method: 'Extract.Review.ChangeFields',
|
|
1501
|
+
example:
|
|
1502
|
+
'ReviewChangeFieldsParams parameters = new()\n{\n JobID = "job_id",\n Changes =\n [\n new()\n {\n Change = Change.Correct,\n Path = "/total",\n Value = JsonSerializer.SerializeToElement(1250.5),\n },\n ],\n Revision = 0,\n};\n\nvar extractReview = await client.Extract.Review.ChangeFields(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1503
|
+
},
|
|
1504
|
+
typescript: {
|
|
1505
|
+
method: 'client.extract.review.changeFields',
|
|
1506
|
+
example:
|
|
1507
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.changeFields('job_id', {\n changes: [{ change: 'correct', path: '/total' }],\n revision: 0,\n});\n\nconsole.log(extractReview.id);",
|
|
1508
|
+
},
|
|
1509
|
+
http: {
|
|
1510
|
+
example:
|
|
1511
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review/fields \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "changes": [\n {\n "change": "correct",\n "path": "/total"\n }\n ],\n "revision": 0\n }\'',
|
|
1512
|
+
},
|
|
1513
|
+
cli: {
|
|
1514
|
+
method: 'review change_fields',
|
|
1515
|
+
example:
|
|
1516
|
+
"llp extract:review change-fields \\\n --api-key 'My API Key' \\\n --job-id job_id \\\n --change '{change: correct, path: /total}' \\\n --revision 0",
|
|
1517
|
+
},
|
|
1518
|
+
},
|
|
1519
|
+
},
|
|
1520
|
+
{
|
|
1521
|
+
name: 'approve',
|
|
1522
|
+
endpoint: '/api/v2/extract/{job_id}/review/approve',
|
|
1523
|
+
httpMethod: 'post',
|
|
1524
|
+
summary: 'Approve Extract Review',
|
|
1525
|
+
description:
|
|
1526
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nApprove the reviewed result.\n\nWhile flagged fields nobody checked remain, answers 409 with `code: open_flags`\nand their `paths`, unless `sign_off` confirms them as part of approving.\nA job that has not completed answers 409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.",
|
|
1527
|
+
stainlessPath: '(resource) extract.review > (method) approve',
|
|
1528
|
+
qualified: 'client.extract.review.approve',
|
|
1529
|
+
params: [
|
|
1530
|
+
'job_id: string;',
|
|
1531
|
+
'revision: number;',
|
|
1532
|
+
'organization_id?: string;',
|
|
1533
|
+
'project_id?: string;',
|
|
1534
|
+
'sign_off?: boolean;',
|
|
1535
|
+
],
|
|
1536
|
+
response:
|
|
1537
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1538
|
+
markdown:
|
|
1539
|
+
"## approve\n\n`client.extract.review.approve(job_id: string, revision: number, organization_id?: string, project_id?: string, sign_off?: boolean): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**post** `/api/v2/extract/{job_id}/review/approve`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nApprove the reviewed result.\n\nWhile flagged fields nobody checked remain, answers 409 with `code: open_flags`\nand their `paths`, unless `sign_off` confirms them as part of approving.\nA job that has not completed answers 409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.\n\n### Parameters\n\n- `job_id: string`\n\n- `revision: number`\n The review's revision as the caller last read it.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `sign_off?: boolean`\n Confirm the flagged fields nobody checked as part of approving.\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.approve('job_id', { revision: 0 });\n\nconsole.log(extractReview);\n```",
|
|
1540
|
+
perLanguage: {
|
|
1541
|
+
python: {
|
|
1542
|
+
method: 'extract.review.approve',
|
|
1543
|
+
example:
|
|
1544
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.approve(\n job_id="job_id",\n revision=0,\n)\nprint(extract_review.id)',
|
|
1545
|
+
},
|
|
1546
|
+
go: {
|
|
1547
|
+
method: 'client.Extract.Review.Approve',
|
|
1548
|
+
example:
|
|
1549
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.Approve(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewApproveParams{\n\t\t\tRevision: 0,\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1550
|
+
},
|
|
1551
|
+
java: {
|
|
1552
|
+
method: 'extract().review().approve',
|
|
1553
|
+
example:
|
|
1554
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewApproveParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ReviewApproveParams params = ReviewApproveParams.builder()\n .jobId("job_id")\n .revision(0L)\n .build();\n ExtractReview extractReview = client.extract().review().approve(params);\n }\n}',
|
|
1555
|
+
},
|
|
1556
|
+
csharp: {
|
|
1557
|
+
method: 'Extract.Review.Approve',
|
|
1558
|
+
example:
|
|
1559
|
+
'ReviewApproveParams parameters = new()\n{\n JobID = "job_id",\n Revision = 0,\n};\n\nvar extractReview = await client.Extract.Review.Approve(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1560
|
+
},
|
|
1561
|
+
typescript: {
|
|
1562
|
+
method: 'client.extract.review.approve',
|
|
1563
|
+
example:
|
|
1564
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.approve('job_id', { revision: 0 });\n\nconsole.log(extractReview.id);",
|
|
1565
|
+
},
|
|
1566
|
+
http: {
|
|
1567
|
+
example:
|
|
1568
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review/approve \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "revision": 0\n }\'',
|
|
1569
|
+
},
|
|
1570
|
+
cli: {
|
|
1571
|
+
method: 'review approve',
|
|
1572
|
+
example:
|
|
1573
|
+
"llp extract:review approve \\\n --api-key 'My API Key' \\\n --job-id job_id \\\n --revision 0",
|
|
1574
|
+
},
|
|
1575
|
+
},
|
|
1576
|
+
},
|
|
1577
|
+
{
|
|
1578
|
+
name: 'reject',
|
|
1579
|
+
endpoint: '/api/v2/extract/{job_id}/review/reject',
|
|
1580
|
+
httpMethod: 'post',
|
|
1581
|
+
summary: 'Reject Extract Review',
|
|
1582
|
+
description:
|
|
1583
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nReject the result, with a reason. A job that failed or was cancelled can be rejected,\nwhich closes a review turned on while it ran. A job still queued or running answers\n409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.",
|
|
1584
|
+
stainlessPath: '(resource) extract.review > (method) reject',
|
|
1585
|
+
qualified: 'client.extract.review.reject',
|
|
1586
|
+
params: [
|
|
1587
|
+
'job_id: string;',
|
|
1588
|
+
'reason: string;',
|
|
1589
|
+
'revision: number;',
|
|
1590
|
+
'organization_id?: string;',
|
|
1591
|
+
'project_id?: string;',
|
|
1592
|
+
],
|
|
1593
|
+
response:
|
|
1594
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1595
|
+
markdown:
|
|
1596
|
+
"## reject\n\n`client.extract.review.reject(job_id: string, reason: string, revision: number, organization_id?: string, project_id?: string): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**post** `/api/v2/extract/{job_id}/review/reject`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nReject the result, with a reason. A job that failed or was cancelled can be rejected,\nwhich closes a review turned on while it ran. A job still queued or running answers\n409 with `code: job_not_reviewable`. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.\n\n### Parameters\n\n- `job_id: string`\n\n- `reason: string`\n Why the result was rejected.\n\n- `revision: number`\n The review's revision as the caller last read it.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.reject('job_id', { reason: 'The invoice total does not match the line items.', revision: 0 });\n\nconsole.log(extractReview);\n```",
|
|
1597
|
+
perLanguage: {
|
|
1598
|
+
python: {
|
|
1599
|
+
method: 'extract.review.reject',
|
|
1600
|
+
example:
|
|
1601
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.reject(\n job_id="job_id",\n reason="The invoice total does not match the line items.",\n revision=0,\n)\nprint(extract_review.id)',
|
|
1602
|
+
},
|
|
1603
|
+
go: {
|
|
1604
|
+
method: 'client.Extract.Review.Reject',
|
|
1605
|
+
example:
|
|
1606
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.Reject(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewRejectParams{\n\t\t\tReason: "The invoice total does not match the line items.",\n\t\t\tRevision: 0,\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1607
|
+
},
|
|
1608
|
+
java: {
|
|
1609
|
+
method: 'extract().review().reject',
|
|
1610
|
+
example:
|
|
1611
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewRejectParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ReviewRejectParams params = ReviewRejectParams.builder()\n .jobId("job_id")\n .reason("The invoice total does not match the line items.")\n .revision(0L)\n .build();\n ExtractReview extractReview = client.extract().review().reject(params);\n }\n}',
|
|
1612
|
+
},
|
|
1613
|
+
csharp: {
|
|
1614
|
+
method: 'Extract.Review.Reject',
|
|
1615
|
+
example:
|
|
1616
|
+
'ReviewRejectParams parameters = new()\n{\n JobID = "job_id",\n Reason = "The invoice total does not match the line items.",\n Revision = 0,\n};\n\nvar extractReview = await client.Extract.Review.Reject(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1617
|
+
},
|
|
1618
|
+
typescript: {
|
|
1619
|
+
method: 'client.extract.review.reject',
|
|
1620
|
+
example:
|
|
1621
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.reject('job_id', {\n reason: 'The invoice total does not match the line items.',\n revision: 0,\n});\n\nconsole.log(extractReview.id);",
|
|
1622
|
+
},
|
|
1623
|
+
http: {
|
|
1624
|
+
example:
|
|
1625
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review/reject \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "reason": "The invoice total does not match the line items.",\n "revision": 0\n }\'',
|
|
1626
|
+
},
|
|
1627
|
+
cli: {
|
|
1628
|
+
method: 'review reject',
|
|
1629
|
+
example:
|
|
1630
|
+
"llp extract:review reject \\\n --api-key 'My API Key' \\\n --job-id job_id \\\n --reason 'The invoice total does not match the line items.' \\\n --revision 0",
|
|
1631
|
+
},
|
|
1632
|
+
},
|
|
1633
|
+
},
|
|
1634
|
+
{
|
|
1635
|
+
name: 'reopen',
|
|
1636
|
+
endpoint: '/api/v2/extract/{job_id}/review/reopen',
|
|
1637
|
+
httpMethod: 'post',
|
|
1638
|
+
summary: 'Reopen Extract Review',
|
|
1639
|
+
description:
|
|
1640
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nPut an approved or rejected review back to pending. Its field actions stay.\n\nA `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.",
|
|
1641
|
+
stainlessPath: '(resource) extract.review > (method) reopen',
|
|
1642
|
+
qualified: 'client.extract.review.reopen',
|
|
1643
|
+
params: ['job_id: string;', 'revision: number;', 'organization_id?: string;', 'project_id?: string;'],
|
|
1644
|
+
response:
|
|
1645
|
+
"{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }",
|
|
1646
|
+
markdown:
|
|
1647
|
+
"## reopen\n\n`client.extract.review.reopen(job_id: string, revision: number, organization_id?: string, project_id?: string): { id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: object[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n\n**post** `/api/v2/extract/{job_id}/review/reopen`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nPut an approved or rejected review back to pending. Its field actions stay.\n\nA `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`.\n\n### Parameters\n\n- `job_id: string`\n\n- `revision: number`\n The review's revision as the caller last read it.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; confidence_threshold: number; created_at: string; decided_at: string; decided_by: string; decided_reason: string; field_actions: object; fields_in_scope: string[]; flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]; job_id: string; open_flags: string[]; original_result: object; required_fields: string[]; retain_until: string; reviewed_result: object; revision: number; source_file_id: string; status: 'approved' | 'pending' | 'rejected'; updated_at: string; }`\n An extract job's review: its settings, flags, field actions and decision,\nwith the result as read and as reviewed.\n\n - `id: string`\n - `confidence_threshold: number`\n - `created_at: string`\n - `decided_at: string`\n - `decided_by: string`\n - `decided_reason: string`\n - `field_actions: object`\n - `fields_in_scope: string[]`\n - `flags: { handled: boolean; path: string; reason: 'below_threshold' | 'required_empty'; cell?: { row: number; column?: string; }; confidence?: number; }[]`\n - `job_id: string`\n - `open_flags: string[]`\n - `original_result: object`\n - `required_fields: string[]`\n - `retain_until: string`\n - `reviewed_result: object`\n - `revision: number`\n - `source_file_id: string`\n - `status: 'approved' | 'pending' | 'rejected'`\n - `updated_at: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst extractReview = await client.extract.review.reopen('job_id', { revision: 0 });\n\nconsole.log(extractReview);\n```",
|
|
1648
|
+
perLanguage: {
|
|
1649
|
+
python: {
|
|
1650
|
+
method: 'extract.review.reopen',
|
|
1651
|
+
example:
|
|
1652
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\nextract_review = client.extract.review.reopen(\n job_id="job_id",\n revision=0,\n)\nprint(extract_review.id)',
|
|
1653
|
+
},
|
|
1654
|
+
go: {
|
|
1655
|
+
method: 'client.Extract.Review.Reopen',
|
|
1656
|
+
example:
|
|
1657
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\textractReview, err := client.Extract.Review.Reopen(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewReopenParams{\n\t\t\tRevision: 0,\n\t\t},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", extractReview.ID)\n}\n',
|
|
1658
|
+
},
|
|
1659
|
+
java: {
|
|
1660
|
+
method: 'extract().review().reopen',
|
|
1661
|
+
example:
|
|
1662
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ExtractReview;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewReopenParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ReviewReopenParams params = ReviewReopenParams.builder()\n .jobId("job_id")\n .revision(0L)\n .build();\n ExtractReview extractReview = client.extract().review().reopen(params);\n }\n}',
|
|
1663
|
+
},
|
|
1664
|
+
csharp: {
|
|
1665
|
+
method: 'Extract.Review.Reopen',
|
|
1666
|
+
example:
|
|
1667
|
+
'ReviewReopenParams parameters = new()\n{\n JobID = "job_id",\n Revision = 0,\n};\n\nvar extractReview = await client.Extract.Review.Reopen(parameters);\n\nConsole.WriteLine(extractReview);',
|
|
1668
|
+
},
|
|
1669
|
+
typescript: {
|
|
1670
|
+
method: 'client.extract.review.reopen',
|
|
1671
|
+
example:
|
|
1672
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst extractReview = await client.extract.review.reopen('job_id', { revision: 0 });\n\nconsole.log(extractReview.id);",
|
|
1673
|
+
},
|
|
1674
|
+
http: {
|
|
1675
|
+
example:
|
|
1676
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review/reopen \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "revision": 0\n }\'',
|
|
1677
|
+
},
|
|
1678
|
+
cli: {
|
|
1679
|
+
method: 'review reopen',
|
|
1680
|
+
example:
|
|
1681
|
+
"llp extract:review reopen \\\n --api-key 'My API Key' \\\n --job-id job_id \\\n --revision 0",
|
|
1682
|
+
},
|
|
1683
|
+
},
|
|
1684
|
+
},
|
|
1685
|
+
{
|
|
1686
|
+
name: 'list_events',
|
|
1687
|
+
endpoint: '/api/v2/extract/{job_id}/review/events',
|
|
1688
|
+
httpMethod: 'get',
|
|
1689
|
+
summary: 'List Extract Review Events',
|
|
1690
|
+
description:
|
|
1691
|
+
"Beta: answers 403 until extract review is enabled for the caller and their organization.\n\nList a review's history, newest first.",
|
|
1692
|
+
stainlessPath: '(resource) extract.review > (method) list_events',
|
|
1693
|
+
qualified: 'client.extract.review.listEvents',
|
|
1694
|
+
params: [
|
|
1695
|
+
'job_id: string;',
|
|
1696
|
+
'organization_id?: string;',
|
|
1697
|
+
'page_size?: number;',
|
|
1698
|
+
'page_token?: string;',
|
|
1699
|
+
'project_id?: string;',
|
|
1700
|
+
],
|
|
1701
|
+
response:
|
|
1702
|
+
"{ id: string; actor_id: string; created_at: string; kind: string; detail?: { confidence_threshold: number; fields_in_scope: string[]; origin: 'api' | 'edit' | 'history' | 'policy' | 'run'; required_fields: string[]; } | { reason: string; } | { paths: string[]; }; path?: string; value_after?: object; value_before?: object; }",
|
|
1703
|
+
markdown:
|
|
1704
|
+
"## list_events\n\n`client.extract.review.listEvents(job_id: string, organization_id?: string, page_size?: number, page_token?: string, project_id?: string): { id: string; actor_id: string; created_at: string; kind: string; detail?: object | object | object; path?: string; value_after?: object; value_before?: object; }`\n\n**get** `/api/v2/extract/{job_id}/review/events`\n\nBeta: answers 403 until extract review is enabled for the caller and their organization.\n\nList a review's history, newest first.\n\n### Parameters\n\n- `job_id: string`\n\n- `organization_id?: string`\n\n- `page_size?: number`\n Events per page.\n\n- `page_token?: string`\n Token from the previous page.\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; actor_id: string; created_at: string; kind: string; detail?: { confidence_threshold: number; fields_in_scope: string[]; origin: 'api' | 'edit' | 'history' | 'policy' | 'run'; required_fields: string[]; } | { reason: string; } | { paths: string[]; }; path?: string; value_after?: object; value_before?: object; }`\n One entry in a review's history.\n\n - `id: string`\n - `actor_id: string`\n - `created_at: string`\n - `kind: string`\n - `detail?: { confidence_threshold: number; fields_in_scope: string[]; origin: 'api' | 'edit' | 'history' | 'policy' | 'run'; required_fields: string[]; } | { reason: string; } | { paths: string[]; }`\n - `path?: string`\n - `value_after?: object`\n - `value_before?: object`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const extractReviewEvent of client.extract.review.listEvents('job_id')) {\n console.log(extractReviewEvent);\n}\n```",
|
|
1705
|
+
perLanguage: {
|
|
1706
|
+
python: {
|
|
1707
|
+
method: 'extract.review.list_events',
|
|
1708
|
+
example:
|
|
1709
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\npage = client.extract.review.list_events(\n job_id="job_id",\n)\npage = page.items[0]\nprint(page.id)',
|
|
1710
|
+
},
|
|
1711
|
+
go: {
|
|
1712
|
+
method: 'client.Extract.Review.ListEvents',
|
|
1713
|
+
example:
|
|
1714
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\tpage, err := client.Extract.Review.ListEvents(\n\t\tcontext.TODO(),\n\t\t"job_id",\n\t\tllamacloud.ExtractReviewListEventsParams{},\n\t)\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", page)\n}\n',
|
|
1715
|
+
},
|
|
1716
|
+
java: {
|
|
1717
|
+
method: 'extract().review().listEvents',
|
|
1718
|
+
example:
|
|
1719
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewListEventsPage;\nimport ai.llamaindex.llamacloud.models.extract.review.ReviewListEventsParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n ReviewListEventsPage page = client.extract().review().listEvents("job_id");\n }\n}',
|
|
1720
|
+
},
|
|
1721
|
+
csharp: {
|
|
1722
|
+
method: 'Extract.Review.ListEvents',
|
|
1723
|
+
example:
|
|
1724
|
+
'ReviewListEventsParams parameters = new() { JobID = "job_id" };\n\nvar page = await client.Extract.Review.ListEvents(parameters);\nawait foreach (var item in page.Paginate())\n{\n Console.WriteLine(item);\n}',
|
|
1725
|
+
},
|
|
1726
|
+
typescript: {
|
|
1727
|
+
method: 'client.extract.review.listEvents',
|
|
1728
|
+
example:
|
|
1729
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\n// Automatically fetches more pages as needed.\nfor await (const extractReviewEvent of client.extract.review.listEvents('job_id')) {\n console.log(extractReviewEvent.id);\n}",
|
|
1730
|
+
},
|
|
1731
|
+
http: {
|
|
1732
|
+
example:
|
|
1733
|
+
'curl https://api.cloud.llamaindex.ai/api/v2/extract/$JOB_ID/review/events \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"',
|
|
1734
|
+
},
|
|
1735
|
+
cli: {
|
|
1736
|
+
method: 'review list_events',
|
|
1737
|
+
example: "llp extract:review list-events \\\n --api-key 'My API Key' \\\n --job-id job_id",
|
|
1738
|
+
},
|
|
1739
|
+
},
|
|
1740
|
+
},
|
|
1355
1741
|
{
|
|
1356
1742
|
name: 'create',
|
|
1357
1743
|
endpoint: '/api/v2/batches',
|
|
@@ -1848,14 +2234,14 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1848
2234
|
qualified: 'client.configurations.create',
|
|
1849
2235
|
params: [
|
|
1850
2236
|
'name: string;',
|
|
1851
|
-
"parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-
|
|
2237
|
+
"parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; };",
|
|
1852
2238
|
'organization_id?: string;',
|
|
1853
2239
|
'project_id?: string;',
|
|
1854
2240
|
],
|
|
1855
2241
|
response:
|
|
1856
2242
|
"{ id: string; name: string; parameters: object | object | object | object | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | object; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
1857
2243
|
markdown:
|
|
1858
|
-
"## create\n\n`client.configurations.create(name: string, parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }, organization_id?: string, project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**post** `/api/v1/beta/configurations`\n\nUpsert a product configuration; updates if one with the same name + product type + project exists, otherwise creates.\n\n### Parameters\n\n- `name: string`\n Human-readable name for this configuration.\n\n- `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Product-specific configuration parameters.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationResponse = await client.configurations.create({\n name: 'x',\n parameters: { product_type: 'classify_v2', rules: [{ description: 'contains invoice number, line items, and total amount', type: 'invoice' }] },\n});\n\nconsole.log(configurationResponse);\n```",
|
|
2244
|
+
"## create\n\n`client.configurations.create(name: string, parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }, organization_id?: string, project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**post** `/api/v1/beta/configurations`\n\nUpsert a product configuration; updates if one with the same name + product type + project exists, otherwise creates.\n\n### Parameters\n\n- `name: string`\n Human-readable name for this configuration.\n\n- `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Product-specific configuration parameters.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationResponse = await client.configurations.create({\n name: 'x',\n parameters: { product_type: 'classify_v2', rules: [{ description: 'contains invoice number, line items, and total amount', type: 'invoice' }] },\n});\n\nconsole.log(configurationResponse);\n```",
|
|
1859
2245
|
perLanguage: {
|
|
1860
2246
|
python: {
|
|
1861
2247
|
method: 'configurations.create',
|
|
@@ -1913,7 +2299,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1913
2299
|
response:
|
|
1914
2300
|
"{ id: string; name: string; parameters: object | object | object | object | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | object; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
1915
2301
|
markdown:
|
|
1916
|
-
"## list\n\n`client.configurations.list(latest_only?: boolean, name?: string, organization_id?: string, page_size?: number, page_token?: string, product_type?: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'[], project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**get** `/api/v1/beta/configurations`\n\nList product configurations for the current project.\n\n### Parameters\n\n- `latest_only?: boolean`\n Return only the latest version per configuration name.\n\n- `name?: string`\n Filter by configuration name.\n\n- `organization_id?: string`\n\n- `page_size?: number`\n Number of items per page.\n\n- `page_token?: string`\n Pagination token.\n\n- `product_type?: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'[]`\n Filter by one or more product types. Repeat the parameter for multiple values.\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-
|
|
2302
|
+
"## list\n\n`client.configurations.list(latest_only?: boolean, name?: string, organization_id?: string, page_size?: number, page_token?: string, product_type?: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'[], project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**get** `/api/v1/beta/configurations`\n\nList product configurations for the current project.\n\n### Parameters\n\n- `latest_only?: boolean`\n Return only the latest version per configuration name.\n\n- `name?: string`\n Filter by configuration name.\n\n- `organization_id?: string`\n\n- `page_size?: number`\n Number of items per page.\n\n- `page_token?: string`\n Pagination token.\n\n- `product_type?: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'[]`\n Filter by one or more product types. Repeat the parameter for multiple values.\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const configurationResponse of client.configurations.list()) {\n console.log(configurationResponse);\n}\n```",
|
|
1917
2303
|
perLanguage: {
|
|
1918
2304
|
python: {
|
|
1919
2305
|
method: 'configurations.list',
|
|
@@ -1962,7 +2348,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
1962
2348
|
response:
|
|
1963
2349
|
"{ id: string; name: string; parameters: object | object | object | object | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | object; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
1964
2350
|
markdown:
|
|
1965
|
-
"## retrieve\n\n`client.configurations.retrieve(config_id: string, organization_id?: string, project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**get** `/api/v1/beta/configurations/{config_id}`\n\nGet a single product configuration by ID.\n\n### Parameters\n\n- `config_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-
|
|
2351
|
+
"## retrieve\n\n`client.configurations.retrieve(config_id: string, organization_id?: string, project_id?: string): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**get** `/api/v1/beta/configurations/{config_id}`\n\nGet a single product configuration by ID.\n\n### Parameters\n\n- `config_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationResponse = await client.configurations.retrieve('config_id');\n\nconsole.log(configurationResponse);\n```",
|
|
1966
2352
|
perLanguage: {
|
|
1967
2353
|
python: {
|
|
1968
2354
|
method: 'configurations.retrieve',
|
|
@@ -2012,12 +2398,12 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
2012
2398
|
'organization_id?: string;',
|
|
2013
2399
|
'project_id?: string;',
|
|
2014
2400
|
'name?: string;',
|
|
2015
|
-
"parameters?: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-
|
|
2401
|
+
"parameters?: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; };",
|
|
2016
2402
|
],
|
|
2017
2403
|
response:
|
|
2018
2404
|
"{ id: string; name: string; parameters: object | object | object | object | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | object; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
2019
2405
|
markdown:
|
|
2020
|
-
"## update\n\n`client.configurations.update(config_id: string, organization_id?: string, project_id?: string, name?: string, parameters?: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**put** `/api/v1/beta/configurations/{config_id}`\n\nUpdate an existing product configuration.\n\n### Parameters\n\n- `config_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `name?: string`\n Updated name (omit to leave unchanged).\n\n- `parameters?: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Updated parameters (omit to leave unchanged).\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-10-16' | '2026-09-28' | '2026-06-15' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationResponse = await client.configurations.update('config_id');\n\nconsole.log(configurationResponse);\n```",
|
|
2406
|
+
"## update\n\n`client.configurations.update(config_id: string, organization_id?: string, project_id?: string, name?: string, parameters?: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }): { id: string; name: string; parameters: classify_v2_parameters | extract_v2_parameters | parse_v2_parameters | split_v1_parameters | object | untyped_parameters; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n\n**put** `/api/v1/beta/configurations/{config_id}`\n\nUpdate an existing product configuration.\n\n### Parameters\n\n- `config_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `name?: string`\n Updated name (omit to leave unchanged).\n\n- `parameters?: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Updated parameters (omit to leave unchanged).\n\n### Returns\n\n- `{ id: string; name: string; parameters: { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: object; client_name?: string; crop_box?: object; disable_cache?: boolean; fast_options?: object; input_options?: object; output_options?: object; page_ranges?: object; processing_control?: object; processing_options?: object; webhook_configuration_ids?: string[]; webhook_configurations?: object[]; } | { categories: split_category[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: object; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }`\n Response schema for a single product configuration.\n\n - `id: string`\n - `name: string`\n - `parameters: { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { data_schema: object; product_type: 'extract_v2'; advanced_citations?: boolean; cite_sources?: boolean; confidence_scores?: boolean; disable_cache?: boolean; effort?: 'max'; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; sheet_names?: string[]; spreadsheet_mode?: boolean; system_prompt?: string; target_pages?: string; tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'turbo'; version?: string; } | { product_type: 'parse_v2'; tier: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; version: 'latest' | '2026-11-19' | '2026-11-12' | '2026-11-09' | string; agentic_options?: { custom_prompt?: string; }; client_name?: string; crop_box?: { bottom?: number; left?: number; right?: number; top?: number; }; disable_cache?: boolean; fast_options?: object; input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; image?: { camera_photo_correction?: boolean; }; pdf?: object; presentation?: { include_hidden_slides?: boolean; out_of_bounds_content?: boolean; skip_embedded_data?: boolean; }; spreadsheet?: { detect_sub_tables_in_sheets?: boolean; force_formula_computation_in_sheets?: boolean; include_hidden_sheets?: boolean; }; }; output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'char' | 'line' | 'word'[]; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; markdown?: { annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; inline_images?: boolean; tables?: object; }; save_output_pdf?: boolean; spatial_text?: { do_not_unroll_columns?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; }; tables_as_spreadsheet?: { enable?: boolean; guess_sheet_name?: boolean; }; watermark_handling?: 'move_to_end' | 'move_to_start' | 'remove'; }; page_ranges?: { max_pages?: number; target_pages?: string; }; processing_control?: { job_failure_conditions?: { allowed_page_failure_ratio?: number; fail_on_buggy_font?: boolean; fail_on_image_extraction_error?: boolean; fail_on_image_ocr_error?: boolean; fail_on_markdown_reconstruction_error?: boolean; }; timeouts?: { base_in_seconds?: number; extra_time_per_page_in_seconds?: number; }; }; processing_options?: { aggressive_table_extraction?: boolean; auto_mode_configuration?: { parsing_conf: object; document_longer_than_n_pages?: number; document_shorter_than_n_pages?: number; filename_match_glob?: string; filename_match_glob_list?: string[]; filename_regexp?: string; filename_regexp_mode?: string; full_page_image_in_page?: boolean; full_page_image_in_page_threshold?: number | string; image_in_page?: boolean; layout_element_in_page?: string; layout_element_in_page_confidence_threshold?: number | string; min_complexity?: 'high' | 'low' | 'medium'; page_contains_at_least_n_charts?: number | string; page_contains_at_least_n_images?: number | string; page_contains_at_least_n_layout_elements?: number | string; page_contains_at_least_n_lines?: number | string; page_contains_at_least_n_links?: number | string; page_contains_at_least_n_numbers?: number | string; page_contains_at_least_n_percent_numbers?: number | string; page_contains_at_least_n_tables?: number | string; page_contains_at_least_n_words?: number | string; page_contains_at_most_n_charts?: number | string; page_contains_at_most_n_images?: number | string; page_contains_at_most_n_layout_elements?: number | string; page_contains_at_most_n_lines?: number | string; page_contains_at_most_n_links?: number | string; page_contains_at_most_n_numbers?: number | string; page_contains_at_most_n_percent_numbers?: number | string; page_contains_at_most_n_tables?: number | string; page_contains_at_most_n_words?: number | string; page_longer_than_n_chars?: number | string; page_md_error?: boolean; page_shorter_than_n_chars?: number | string; regexp_in_page?: string; regexp_in_page_mode?: string; table_in_page?: boolean; text_in_page?: string; trigger_mode?: string; }[]; confidence_score_effort?: 'high'; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; forms?: 'default' | 'enrich'; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic' | 'agentic_plus' | 'efficient'; }; webhook_configuration_ids?: string[]; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'json' | 'string'; webhook_signing_secret?: string; webhook_url?: string; }[]; } | { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; parse_config_id?: string; parse_tier?: 'agentic' | 'agentic_plus' | 'cost_effective' | 'fast'; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; target_pages?: string; version?: string; } | { product_type: 'spreadsheet_v1'; extraction_range?: string; flatten_hierarchical_tables?: boolean; generate_additional_metadata?: boolean; include_hidden_cells?: boolean; sheet_names?: string[]; specialization?: string; table_merge_sensitivity?: 'strong' | 'weak'; tier?: 'agentic' | 'cost_effective'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'classify_v2' | 'extract_v2' | 'parse_v2' | 'split_v1' | 'spreadsheet_v1' | 'unknown'`\n - `version: string`\n - `created_at?: string`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst configurationResponse = await client.configurations.update('config_id');\n\nconsole.log(configurationResponse);\n```",
|
|
2021
2407
|
perLanguage: {
|
|
2022
2408
|
python: {
|
|
2023
2409
|
method: 'configurations.update',
|
|
@@ -3253,7 +3639,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3253
3639
|
httpMethod: 'get',
|
|
3254
3640
|
summary: 'Search Pipelines',
|
|
3255
3641
|
description:
|
|
3256
|
-
'Search for pipelines by name, type, or project.\n\nDeprecated: use `GET /api/v2/pipelines`, which is paginated.',
|
|
3642
|
+
'Search for pipelines by name, type, or project.\n\nLegacy pipelines with unavailable embedding configurations return `embedding_config: null`.\n\nUnavailable linked model configurations return `embedding_model_config: null`, retaining their IDs. A stored-config fallback in this list does not repair the pipeline; detail reads and retrieval still require valid configuration.\n\nDeprecated: use `GET /api/v2/pipelines`, which is paginated.',
|
|
3257
3643
|
stainlessPath: '(resource) pipelines > (method) list',
|
|
3258
3644
|
qualified: 'client.pipelines.list',
|
|
3259
3645
|
params: [
|
|
@@ -3266,32 +3652,32 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3266
3652
|
response:
|
|
3267
3653
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }[]",
|
|
3268
3654
|
markdown:
|
|
3269
|
-
"## list\n\n`client.pipelines.list(organization_id?: string, pipeline_name?: string, pipeline_type?: 'MANAGED' | 'PLAYGROUND', project_id?: string, project_name?: string): object[]`\n\n**get** `/api/v1/pipelines`\n\nSearch for pipelines by name, type, or project.\n\nDeprecated: use `GET /api/v2/pipelines`, which is paginated.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `pipeline_name?: string`\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Enum for representing the type of a pipeline\n\n- `project_id?: string`\n\n- `project_name?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst
|
|
3655
|
+
"## list\n\n`client.pipelines.list(organization_id?: string, pipeline_name?: string, pipeline_type?: 'MANAGED' | 'PLAYGROUND', project_id?: string, project_name?: string): object[]`\n\n**get** `/api/v1/pipelines`\n\nSearch for pipelines by name, type, or project.\n\nLegacy pipelines with unavailable embedding configurations return `embedding_config: null`.\n\nUnavailable linked model configurations return `embedding_model_config: null`, retaining their IDs. A stored-config fallback in this list does not repair the pipeline; detail reads and retrieval still require valid configuration.\n\nDeprecated: use `GET /api/v2/pipelines`, which is paginated.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `pipeline_name?: string`\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Enum for representing the type of a pipeline\n\n- `project_id?: string`\n\n- `project_name?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipelineListItems = await client.pipelines.list();\n\nconsole.log(pipelineListItems);\n```",
|
|
3270
3656
|
perLanguage: {
|
|
3271
3657
|
python: {
|
|
3272
3658
|
method: 'pipelines.list',
|
|
3273
3659
|
example:
|
|
3274
|
-
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\
|
|
3660
|
+
'import os\nfrom llama_cloud import LlamaCloud\n\nclient = LlamaCloud(\n api_key=os.environ.get("LLAMA_CLOUD_API_KEY"), # This is the default and can be omitted\n)\npipeline_list_items = client.pipelines.list()\nprint(pipeline_list_items)',
|
|
3275
3661
|
},
|
|
3276
3662
|
go: {
|
|
3277
3663
|
method: 'client.Pipelines.List',
|
|
3278
3664
|
example:
|
|
3279
|
-
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\
|
|
3665
|
+
'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\tpipelineListItems, err := client.Pipelines.List(context.TODO(), llamacloud.PipelineListParams{})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", pipelineListItems)\n}\n',
|
|
3280
3666
|
},
|
|
3281
3667
|
java: {
|
|
3282
3668
|
method: 'pipelines().list',
|
|
3283
3669
|
example:
|
|
3284
|
-
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.pipelines.
|
|
3670
|
+
'package ai.llamaindex.llamacloud.example;\n\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.pipelines.PipelineListItem;\nimport ai.llamaindex.llamacloud.models.pipelines.PipelineListParams;\n\npublic final class Main {\n private Main() {}\n\n public static void main(String[] args) {\n LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\n List<PipelineListItem> pipelineListItems = client.pipelines().list();\n }\n}',
|
|
3285
3671
|
},
|
|
3286
3672
|
csharp: {
|
|
3287
3673
|
method: 'Pipelines.List',
|
|
3288
3674
|
example:
|
|
3289
|
-
'PipelineListParams parameters = new();\n\nvar
|
|
3675
|
+
'PipelineListParams parameters = new();\n\nvar pipelineListItems = await client.Pipelines.List(parameters);\n\nConsole.WriteLine(pipelineListItems);',
|
|
3290
3676
|
},
|
|
3291
3677
|
typescript: {
|
|
3292
3678
|
method: 'client.pipelines.list',
|
|
3293
3679
|
example:
|
|
3294
|
-
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst
|
|
3680
|
+
"import LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud({\n apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted\n});\n\nconst pipelineListItems = await client.pipelines.list();\n\nconsole.log(pipelineListItems);",
|
|
3295
3681
|
},
|
|
3296
3682
|
http: {
|
|
3297
3683
|
example:
|
|
@@ -3376,7 +3762,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3376
3762
|
'data_sink_id?: string;',
|
|
3377
3763
|
"embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; };",
|
|
3378
3764
|
'embedding_model_config_id?: string;',
|
|
3379
|
-
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
3765
|
+
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
3380
3766
|
'managed_pipeline_id?: string;',
|
|
3381
3767
|
'metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; };',
|
|
3382
3768
|
"pipeline_type?: 'MANAGED' | 'PLAYGROUND';",
|
|
@@ -3388,7 +3774,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3388
3774
|
response:
|
|
3389
3775
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3390
3776
|
markdown:
|
|
3391
|
-
"## create\n\n`client.pipelines.create(name: string, organization_id?: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, pipeline_type?: 'MANAGED' | 'PLAYGROUND', preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines`\n\nCreate a new managed ingestion pipeline.\n\nA pipeline connects data sources to a vector store for RAG.\nAfter creation, call `POST /pipelines/{id}/sync` to start\ningesting documents.\n\n### Parameters\n\n- `name: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Type of pipeline. Either PLAYGROUND or MANAGED.\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Preset retrieval parameters for the pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.create({ name: 'x' });\n\nconsole.log(pipeline);\n```",
|
|
3777
|
+
"## create\n\n`client.pipelines.create(name: string, organization_id?: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, pipeline_type?: 'MANAGED' | 'PLAYGROUND', preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines`\n\nCreate a new managed ingestion pipeline.\n\nA pipeline connects data sources to a vector store for RAG.\nAfter creation, call `POST /pipelines/{id}/sync` to start\ningesting documents.\n\n### Parameters\n\n- `name: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Type of pipeline. Either PLAYGROUND or MANAGED.\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Preset retrieval parameters for the pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.create({ name: 'x' });\n\nconsole.log(pipeline);\n```",
|
|
3392
3778
|
perLanguage: {
|
|
3393
3779
|
python: {
|
|
3394
3780
|
method: 'pipelines.create',
|
|
@@ -3437,7 +3823,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3437
3823
|
response:
|
|
3438
3824
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3439
3825
|
markdown:
|
|
3440
|
-
"## get\n\n`client.pipelines.get(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**get** `/api/v1/pipelines/{pipeline_id}`\n\nGet a pipeline by ID.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.get('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3826
|
+
"## get\n\n`client.pipelines.get(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**get** `/api/v1/pipelines/{pipeline_id}`\n\nGet a pipeline by ID.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.get('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3441
3827
|
perLanguage: {
|
|
3442
3828
|
python: {
|
|
3443
3829
|
method: 'pipelines.get',
|
|
@@ -3490,7 +3876,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3490
3876
|
'data_sink_id?: string;',
|
|
3491
3877
|
"embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; };",
|
|
3492
3878
|
'embedding_model_config_id?: string;',
|
|
3493
|
-
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
3879
|
+
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
3494
3880
|
'managed_pipeline_id?: string;',
|
|
3495
3881
|
'metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; };',
|
|
3496
3882
|
'name?: string;',
|
|
@@ -3502,7 +3888,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3502
3888
|
response:
|
|
3503
3889
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3504
3890
|
markdown:
|
|
3505
|
-
"## update\n\n`client.pipelines.update(pipeline_id: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, name?: string, preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**put** `/api/v1/pipelines/{pipeline_id}`\n\nUpdate an existing pipeline's configuration.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `name?: string`\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Schema for the search params for an retrieval execution that can be preset for a pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.update('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3891
|
+
"## update\n\n`client.pipelines.update(pipeline_id: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, name?: string, preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**put** `/api/v1/pipelines/{pipeline_id}`\n\nUpdate an existing pipeline's configuration.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `name?: string`\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Schema for the search params for an retrieval execution that can be preset for a pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.update('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3506
3892
|
perLanguage: {
|
|
3507
3893
|
python: {
|
|
3508
3894
|
method: 'pipelines.update',
|
|
@@ -3657,7 +4043,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3657
4043
|
'data_sink_id?: string;',
|
|
3658
4044
|
"embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; };",
|
|
3659
4045
|
'embedding_model_config_id?: string;',
|
|
3660
|
-
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
4046
|
+
"llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; };",
|
|
3661
4047
|
'managed_pipeline_id?: string;',
|
|
3662
4048
|
'metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; };',
|
|
3663
4049
|
"pipeline_type?: 'MANAGED' | 'PLAYGROUND';",
|
|
@@ -3669,7 +4055,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3669
4055
|
response:
|
|
3670
4056
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3671
4057
|
markdown:
|
|
3672
|
-
"## upsert\n\n`client.pipelines.upsert(name: string, organization_id?: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, pipeline_type?: 'MANAGED' | 'PLAYGROUND', preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**put** `/api/v1/pipelines`\n\nUpsert a pipeline.\n\nUpdates the pipeline if one with the same name and project\nalready exists, otherwise creates a new one.\n\n### Parameters\n\n- `name: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Type of pipeline. Either PLAYGROUND or MANAGED.\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Preset retrieval parameters for the pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.upsert({ name: 'x' });\n\nconsole.log(pipeline);\n```",
|
|
4058
|
+
"## upsert\n\n`client.pipelines.upsert(name: string, organization_id?: string, project_id?: string, data_sink?: { component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }, data_sink_id?: string, embedding_config?: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }, embedding_model_config_id?: string, llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }, managed_pipeline_id?: string, metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }, pipeline_type?: 'MANAGED' | 'PLAYGROUND', preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }, sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }, status?: string, transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**put** `/api/v1/pipelines`\n\nUpsert a pipeline.\n\nUpdates the pipeline if one with the same name and project\nalready exists, otherwise creates a new one.\n\n### Parameters\n\n- `name: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `data_sink?: { component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; }`\n Schema for creating a data sink.\n - `component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: { distance_method?: 'cosine' | 'hamming' | 'ip' | 'jaccard' | 'l1' | 'l2'; ef_construction?: number; ef_search?: number; m?: number; vector_type?: 'bit' | 'half_vec' | 'sparse_vec' | 'vector'; }; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }`\n Component that implements the data sink\n - `name: string`\n The name of the data sink.\n - `sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'`\n\n- `data_sink_id?: string`\n Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.\n\n- `embedding_config?: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n\n- `embedding_model_config_id?: string`\n Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID.\n\n- `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline.\n - `adaptive_long_table?: boolean`\n - `aggressive_table_extraction?: boolean`\n - `annotate_line_numbers?: boolean`\n - `annotate_links?: boolean`\n - `annotate_revisions?: boolean`\n - `auto_mode?: boolean`\n - `auto_mode_configuration_json?: string`\n - `auto_mode_trigger_on_image_in_page?: boolean`\n - `auto_mode_trigger_on_regexp_in_page?: string`\n - `auto_mode_trigger_on_table_in_page?: boolean`\n - `auto_mode_trigger_on_text_in_page?: string`\n - `azure_openai_api_version?: string`\n - `azure_openai_deployment_name?: string`\n - `azure_openai_endpoint?: string`\n - `azure_openai_key?: string`\n - `bbox_bottom?: number`\n - `bbox_left?: number`\n - `bbox_right?: number`\n - `bbox_top?: number`\n - `bounding_box?: string`\n - `compact_markdown_table?: boolean`\n - `complemental_formatting_instruction?: string`\n - `confidence_score_effort?: string`\n - `content_guideline_instruction?: string`\n - `continuous_mode?: boolean`\n - `disable_image_extraction?: boolean`\n - `disable_ocr?: boolean`\n - `disable_reconstruction?: boolean`\n - `do_not_cache?: boolean`\n - `do_not_unroll_columns?: boolean`\n - `enable_cost_optimizer?: boolean`\n - `extract_charts?: boolean`\n - `extract_layout?: boolean`\n - `extract_printed_page_number?: boolean`\n - `fast_mode?: boolean`\n - `formatting_instruction?: string`\n - `gpt4o_api_key?: string`\n - `gpt4o_mode?: boolean`\n - `guess_xlsx_sheet_name?: boolean`\n - `hide_footers?: boolean`\n - `hide_headers?: boolean`\n - `high_res_ocr?: boolean`\n - `html_make_all_elements_visible?: boolean`\n - `html_remove_fixed_elements?: boolean`\n - `html_remove_navigation_elements?: boolean`\n - `http_proxy?: string`\n - `ignore_document_elements_for_layout_detection?: boolean`\n - `images_to_save?: 'embedded' | 'layout' | 'screenshot'[]`\n - `inline_images_in_markdown?: boolean`\n - `input_s3_path?: string`\n - `input_s3_region?: string`\n - `input_url?: string`\n - `internal_is_screenshot_job?: boolean`\n - `invalidate_cache?: boolean`\n - `is_formatting_instruction?: boolean`\n - `job_timeout_extra_time_per_page_in_seconds?: number`\n - `job_timeout_in_seconds?: number`\n - `keep_page_separator_when_merging_tables?: boolean`\n - `languages?: string[]`\n - `layout_aware?: boolean`\n - `line_level_bounding_box?: boolean`\n - `markdown_table_multiline_header_separator?: string`\n - `max_pages?: number`\n - `max_pages_enforced?: number`\n - `merge_tables_across_pages_in_markdown?: boolean`\n - `model?: string`\n - `outlined_table_extraction?: boolean`\n - `output_pdf_of_document?: boolean`\n - `output_s3_path_prefix?: string`\n - `output_s3_region?: string`\n - `output_tables_as_HTML?: boolean`\n - `page_error_tolerance?: number`\n - `page_footer_prefix?: string`\n - `page_footer_suffix?: string`\n - `page_header_prefix?: string`\n - `page_header_suffix?: string`\n - `page_prefix?: string`\n - `page_separator?: string`\n - `page_suffix?: string`\n - `parse_mode?: string`\n Enum for representing the mode of parsing to be used.\n - `parsing_instruction?: string`\n - `precise_bounding_box?: boolean`\n - `premium_mode?: boolean`\n - `presentation_out_of_bounds_content?: boolean`\n - `presentation_skip_embedded_data?: boolean`\n - `preserve_layout_alignment_across_pages?: boolean`\n - `preserve_very_small_text?: boolean`\n - `preset?: string`\n - `priority?: 'critical' | 'high' | 'low' | 'medium'`\n The priority for the request. This field may be ignored or overwritten depending on the organization tier.\n - `project_id?: string`\n - `remove_hidden_text?: boolean`\n - `replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'`\n Enum for representing the different available page error handling modes.\n - `replace_failed_page_with_error_message_prefix?: string`\n - `replace_failed_page_with_error_message_suffix?: string`\n - `save_images?: boolean`\n - `skip_diagonal_text?: boolean`\n - `specialized_chart_parsing_agentic?: boolean`\n - `specialized_chart_parsing_efficient?: boolean`\n - `specialized_chart_parsing_plus?: boolean`\n - `specialized_image_parsing?: boolean`\n - `spreadsheet_extract_sub_tables?: boolean`\n - `spreadsheet_force_formula_computation?: boolean`\n - `spreadsheet_include_hidden_sheets?: boolean`\n - `strict_mode_buggy_font?: boolean`\n - `strict_mode_image_extraction?: boolean`\n - `strict_mode_image_ocr?: boolean`\n - `strict_mode_reconstruction?: boolean`\n - `structured_output?: boolean`\n - `structured_output_json_schema?: string`\n - `structured_output_json_schema_name?: string`\n - `system_prompt?: string`\n - `system_prompt_append?: string`\n - `take_screenshot?: boolean`\n - `target_pages?: string`\n - `tier?: string`\n - `use_vendor_multimodal_model?: boolean`\n - `user_prompt?: string`\n - `vendor_multimodal_api_key?: string`\n - `vendor_multimodal_model_name?: string`\n - `version?: string`\n - `webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n - `webhook_url?: string`\n\n- `managed_pipeline_id?: string`\n The ID of the ManagedPipeline this playground pipeline is linked to.\n\n- `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n Metadata configuration for the pipeline.\n - `excluded_embed_metadata_keys?: string[]`\n List of metadata keys to exclude from embeddings\n - `excluded_llm_metadata_keys?: string[]`\n List of metadata keys to exclude from LLM during retrieval\n\n- `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n Type of pipeline. Either PLAYGROUND or MANAGED.\n\n- `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n Preset retrieval parameters for the pipeline.\n - `alpha?: number`\n Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval.\n - `class_name?: string`\n - `dense_similarity_cutoff?: number`\n Minimum similarity score wrt query for retrieval\n - `dense_similarity_top_k?: number`\n Number of nodes for dense retrieval.\n - `enable_reranking?: boolean`\n Enable reranking for retrieval\n - `files_top_k?: number`\n Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content).\n - `rerank_top_n?: number`\n Number of reranked nodes for returning.\n - `retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'`\n The retrieval mode for the query.\n - `retrieve_image_nodes?: boolean`\n Whether to retrieve image nodes.\n - `retrieve_page_figure_nodes?: boolean`\n Whether to retrieve page figure nodes.\n - `retrieve_page_screenshot_nodes?: boolean`\n Whether to retrieve page screenshot nodes.\n - `search_filters?: { filters: { key: string; value: number | string | string[] | number[] | number[]; operator?: string; } | { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }[]; condition?: 'and' | 'not' | 'or'; }`\n Metadata filters for vector stores.\n - `search_filters_inference_schema?: object`\n JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference.\n - `sparse_similarity_top_k?: number`\n Number of nodes for sparse retrieval.\n\n- `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n Configuration for sparse embedding models used in hybrid search.\n\nThis allows users to choose between Splade and BM25 models for\nsparse retrieval in managed data sinks.\n - `class_name?: string`\n - `model_type?: 'auto' | 'bm25' | 'splade'`\n The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade).\n\n- `status?: string`\n Status of the pipeline deployment.\n\n- `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n Configuration for the transformation.\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.upsert({ name: 'x' });\n\nconsole.log(pipeline);\n```",
|
|
3673
4059
|
perLanguage: {
|
|
3674
4060
|
python: {
|
|
3675
4061
|
method: 'pipelines.upsert',
|
|
@@ -3779,7 +4165,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3779
4165
|
response:
|
|
3780
4166
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3781
4167
|
markdown:
|
|
3782
|
-
"## create\n\n`client.pipelines.sync.create(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/sync`\n\nTrigger an incremental sync for a managed pipeline.\n\nProcesses new and updated documents from data sources and\nfiles, then updates the index for retrieval.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.sync.create('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
4168
|
+
"## create\n\n`client.pipelines.sync.create(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/sync`\n\nTrigger an incremental sync for a managed pipeline.\n\nProcesses new and updated documents from data sources and\nfiles, then updates the index for retrieval.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.sync.create('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3783
4169
|
perLanguage: {
|
|
3784
4170
|
python: {
|
|
3785
4171
|
method: 'pipelines.sync.create',
|
|
@@ -3829,7 +4215,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
3829
4215
|
response:
|
|
3830
4216
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
3831
4217
|
markdown:
|
|
3832
|
-
"## cancel\n\n`client.pipelines.sync.cancel(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/sync/cancel`\n\nCancel all running sync jobs for a pipeline.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.sync.cancel('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
4218
|
+
"## cancel\n\n`client.pipelines.sync.cancel(pipeline_id: string, project_id?: string): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/sync/cancel`\n\nCancel all running sync jobs for a pipeline.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.sync.cancel('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');\n\nconsole.log(pipeline);\n```",
|
|
3833
4219
|
perLanguage: {
|
|
3834
4220
|
python: {
|
|
3835
4221
|
method: 'pipelines.sync.cancel',
|
|
@@ -4093,7 +4479,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
4093
4479
|
response:
|
|
4094
4480
|
"{ id: string; embedding_config: object | object | object | object | object | { component?: object; type?: 'MANAGED_OPENAI_EMBEDDING'; } | object | object; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: object; embedding_model_config?: { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: object; managed_pipeline_id?: string; metadata_config?: object; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: object; sparse_model_config?: object; status?: 'CREATED' | 'DELETING'; transform_config?: object | object; updated_at?: string; }",
|
|
4095
4481
|
markdown:
|
|
4096
|
-
"## sync\n\n`client.pipelines.dataSources.sync(pipeline_id: string, data_source_id: string, project_id?: string, pipeline_file_ids?: string[]): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync`\n\nRun incremental ingestion: pull upstream changes from the data source into the data sink.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `data_source_id: string`\n\n- `project_id?: string`\n\n- `pipeline_file_ids?: string[]`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.dataSources.sync('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', { pipeline_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' });\n\nconsole.log(pipeline);\n```",
|
|
4482
|
+
"## sync\n\n`client.pipelines.dataSources.sync(pipeline_id: string, data_source_id: string, project_id?: string, pipeline_file_ids?: string[]): { id: string; embedding_config: azure_openai_embedding_config | bedrock_embedding_config | cohere_embedding_config | gemini_embedding_config | hugging_face_inference_api_embedding_config | object | openai_embedding_config | vertex_ai_embedding_config; name: string; project_id: string; config_hash?: object; created_at?: string; data_sink?: data_sink; embedding_model_config?: object; embedding_model_config_id?: string; llama_parse_parameters?: llama_parse_parameters; managed_pipeline_id?: string; metadata_config?: pipeline_metadata_config; pipeline_type?: pipeline_type; preset_retrieval_parameters?: preset_retrieval_params; sparse_model_config?: sparse_model_config; status?: 'CREATED' | 'DELETING'; transform_config?: auto_transform_config | advanced_mode_transform_config; updated_at?: string; }`\n\n**post** `/api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync`\n\nRun incremental ingestion: pull upstream changes from the data source into the data sink.\n\n### Parameters\n\n- `pipeline_id: string`\n\n- `data_source_id: string`\n\n- `project_id?: string`\n\n- `pipeline_file_ids?: string[]`\n\n### Returns\n\n- `{ id: string; embedding_config: { component?: azure_openai_embedding; type?: 'AZURE_EMBEDDING'; } | { component?: bedrock_embedding; type?: 'BEDROCK_EMBEDDING'; } | { component?: cohere_embedding; type?: 'COHERE_EMBEDDING'; } | { component?: gemini_embedding; type?: 'GEMINI_EMBEDDING'; } | { component?: hugging_face_inference_api_embedding; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: openai_embedding; type?: 'OPENAI_EMBEDDING'; } | { component?: vertex_text_embedding; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }; created_at?: string; data_sink?: { id: string; component: object | cloud_pinecone_vector_store | cloud_postgres_vector_store | cloud_qdrant_vector_store | cloud_azure_ai_search_vector_store | cloud_mongodb_atlas_vector_search | cloud_milvus_vector_store | cloud_astra_db_vector_store; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }; embedding_model_config?: { id: string; embedding_config: object | object | object | object | object | object | object; name: string; project_id: string; created_at?: string; updated_at?: string; }; embedding_model_config_id?: string; llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: parsing_languages[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: parsing_mode; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: fail_page_mode; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: object[]; webhook_url?: string; }; managed_pipeline_id?: string; metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }; pipeline_type?: 'MANAGED' | 'PLAYGROUND'; preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: retrieval_mode; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: metadata_filters; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }; sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }; status?: 'CREATED' | 'DELETING'; transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: object | object | object | object | object; mode?: 'advanced'; segmentation_config?: object | object | object; }; updated_at?: string; }`\n Schema for a pipeline.\n\n - `id: string`\n - `embedding_config: { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; azure_deployment?: string; azure_endpoint?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'AZURE_EMBEDDING'; } | { component?: { additional_kwargs?: object; aws_access_key_id?: string; aws_secret_access_key?: string; aws_session_token?: string; class_name?: string; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; profile_name?: string; region_name?: string; timeout?: number; }; type?: 'BEDROCK_EMBEDDING'; } | { component?: { api_key: string; class_name?: string; embed_batch_size?: number; embedding_type?: string; input_type?: string; model_name?: string; num_workers?: number; truncate?: string; }; type?: 'COHERE_EMBEDDING'; } | { component?: { api_base?: string; api_key?: string; class_name?: string; embed_batch_size?: number; model_name?: string; num_workers?: number; output_dimensionality?: number; task_type?: string; title?: string; transport?: string; }; type?: 'GEMINI_EMBEDDING'; } | { component?: { token?: string | boolean; class_name?: string; cookies?: object; embed_batch_size?: number; headers?: object; model_name?: string; num_workers?: number; pooling?: 'cls' | 'last' | 'mean'; query_instruction?: string; task?: string; text_instruction?: string; timeout?: number; }; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: { class_name?: string; embed_batch_size?: number; model_name?: 'openai-text-embedding-3-small'; num_workers?: number; }; type?: 'MANAGED_OPENAI_EMBEDDING'; } | { component?: { additional_kwargs?: object; api_base?: string; api_key?: string; api_version?: string; class_name?: string; default_headers?: object; dimensions?: number; embed_batch_size?: number; max_retries?: number; model_name?: string; num_workers?: number; reuse_client?: boolean; timeout?: number; }; type?: 'OPENAI_EMBEDDING'; } | { component?: { client_email: string; location: string; private_key: string; private_key_id: string; project: string; token_uri: string; additional_kwargs?: object; class_name?: string; embed_batch_size?: number; embed_mode?: 'classification' | 'clustering' | 'default' | 'retrieval' | 'similarity'; model_name?: string; num_workers?: number; }; type?: 'VERTEXAI_EMBEDDING'; }`\n - `name: string`\n - `project_id: string`\n - `config_hash?: { embedding_config_hash?: string; parsing_config_hash?: string; transform_config_hash?: string; }`\n - `created_at?: string`\n - `data_sink?: { id: string; component: object | { api_key: string; index_name: string; class_name?: string; insert_kwargs?: object; namespace?: string; supports_nested_metadata_filters?: true; } | { database: string; embed_dim: number; host: string; password: string; port: number; schema_name: string; table_name: string; user: string; class_name?: string; hnsw_settings?: pg_vector_hnsw_settings; hybrid_search?: boolean; perform_setup?: boolean; supports_nested_metadata_filters?: boolean; } | { api_key: string; collection_name: string; url: string; class_name?: string; client_kwargs?: object; max_retries?: number; supports_nested_metadata_filters?: true; } | { search_service_api_key: string; search_service_endpoint: string; class_name?: string; client_id?: string; client_secret?: string; embedding_dimension?: number; filterable_metadata_field_keys?: object; index_name?: string; search_service_api_version?: string; supports_nested_metadata_filters?: true; tenant_id?: string; } | { collection_name: string; db_name: string; mongodb_uri: string; class_name?: string; embedding_dimension?: number; fulltext_index_name?: string; supports_nested_metadata_filters?: boolean; vector_index_name?: string; } | { uri: string; token?: string; class_name?: string; collection_name?: string; embedding_dimension?: number; supports_nested_metadata_filters?: boolean; } | { token: string; api_endpoint: string; collection_name: string; embedding_dimension: number; class_name?: string; keyspace?: string; supports_nested_metadata_filters?: true; }; name: string; project_id: string; sink_type: 'ASTRA_DB' | 'AZUREAI_SEARCH' | 'MILVUS' | 'MONGODB_ATLAS' | 'PINECONE' | 'POSTGRES' | 'QDRANT'; created_at?: string; updated_at?: string; }`\n - `embedding_model_config?: { id: string; embedding_config: { component?: object; type?: 'AZURE_EMBEDDING'; } | { component?: object; type?: 'BEDROCK_EMBEDDING'; } | { component?: object; type?: 'COHERE_EMBEDDING'; } | { component?: object; type?: 'GEMINI_EMBEDDING'; } | { component?: object; type?: 'HUGGINGFACE_API_EMBEDDING'; } | { component?: object; type?: 'OPENAI_EMBEDDING'; } | { component?: object; type?: 'VERTEXAI_EMBEDDING'; }; name: string; project_id: string; created_at?: string; updated_at?: string; }`\n - `embedding_model_config_id?: string`\n - `llama_parse_parameters?: { adaptive_long_table?: boolean; aggressive_table_extraction?: boolean; annotate_line_numbers?: boolean; annotate_links?: boolean; annotate_revisions?: boolean; auto_mode?: boolean; auto_mode_configuration_json?: string; auto_mode_trigger_on_image_in_page?: boolean; auto_mode_trigger_on_regexp_in_page?: string; auto_mode_trigger_on_table_in_page?: boolean; auto_mode_trigger_on_text_in_page?: string; azure_openai_api_version?: string; azure_openai_deployment_name?: string; azure_openai_endpoint?: string; azure_openai_key?: string; bbox_bottom?: number; bbox_left?: number; bbox_right?: number; bbox_top?: number; bounding_box?: string; compact_markdown_table?: boolean; complemental_formatting_instruction?: string; confidence_score_effort?: string; content_guideline_instruction?: string; continuous_mode?: boolean; disable_image_extraction?: boolean; disable_ocr?: boolean; disable_reconstruction?: boolean; do_not_cache?: boolean; do_not_unroll_columns?: boolean; enable_cost_optimizer?: boolean; extract_charts?: boolean; extract_layout?: boolean; extract_printed_page_number?: boolean; fast_mode?: boolean; formatting_instruction?: string; gpt4o_api_key?: string; gpt4o_mode?: boolean; guess_xlsx_sheet_name?: boolean; hide_footers?: boolean; hide_headers?: boolean; high_res_ocr?: boolean; html_make_all_elements_visible?: boolean; html_remove_fixed_elements?: boolean; html_remove_navigation_elements?: boolean; http_proxy?: string; ignore_document_elements_for_layout_detection?: boolean; images_to_save?: 'embedded' | 'layout' | 'screenshot'[]; inline_images_in_markdown?: boolean; input_s3_path?: string; input_s3_region?: string; input_url?: string; internal_is_screenshot_job?: boolean; invalidate_cache?: boolean; is_formatting_instruction?: boolean; job_timeout_extra_time_per_page_in_seconds?: number; job_timeout_in_seconds?: number; keep_page_separator_when_merging_tables?: boolean; languages?: string[]; layout_aware?: boolean; line_level_bounding_box?: boolean; markdown_table_multiline_header_separator?: string; max_pages?: number; max_pages_enforced?: number; merge_tables_across_pages_in_markdown?: boolean; model?: string; outlined_table_extraction?: boolean; output_pdf_of_document?: boolean; output_s3_path_prefix?: string; output_s3_region?: string; output_tables_as_HTML?: boolean; page_error_tolerance?: number; page_footer_prefix?: string; page_footer_suffix?: string; page_header_prefix?: string; page_header_suffix?: string; page_prefix?: string; page_separator?: string; page_suffix?: string; parse_mode?: string; parsing_instruction?: string; precise_bounding_box?: boolean; premium_mode?: boolean; presentation_out_of_bounds_content?: boolean; presentation_skip_embedded_data?: boolean; preserve_layout_alignment_across_pages?: boolean; preserve_very_small_text?: boolean; preset?: string; priority?: 'critical' | 'high' | 'low' | 'medium'; project_id?: string; remove_hidden_text?: boolean; replace_failed_page_mode?: 'blank_page' | 'error_message' | 'raw_text'; replace_failed_page_with_error_message_prefix?: string; replace_failed_page_with_error_message_suffix?: string; save_images?: boolean; skip_diagonal_text?: boolean; specialized_chart_parsing_agentic?: boolean; specialized_chart_parsing_efficient?: boolean; specialized_chart_parsing_plus?: boolean; specialized_image_parsing?: boolean; spreadsheet_extract_sub_tables?: boolean; spreadsheet_force_formula_computation?: boolean; spreadsheet_include_hidden_sheets?: boolean; strict_mode_buggy_font?: boolean; strict_mode_image_extraction?: boolean; strict_mode_image_ocr?: boolean; strict_mode_reconstruction?: boolean; structured_output?: boolean; structured_output_json_schema?: string; structured_output_json_schema_name?: string; system_prompt?: string; system_prompt_append?: string; take_screenshot?: boolean; target_pages?: string; tier?: string; use_vendor_multimodal_model?: boolean; user_prompt?: string; vendor_multimodal_api_key?: string; vendor_multimodal_model_name?: string; version?: string; webhook_configurations?: { id?: string; webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_signing_secret?: string; webhook_url?: string; }[]; webhook_url?: string; }`\n - `managed_pipeline_id?: string`\n - `metadata_config?: { excluded_embed_metadata_keys?: string[]; excluded_llm_metadata_keys?: string[]; }`\n - `pipeline_type?: 'MANAGED' | 'PLAYGROUND'`\n - `preset_retrieval_parameters?: { alpha?: number; class_name?: string; dense_similarity_cutoff?: number; dense_similarity_top_k?: number; enable_reranking?: boolean; files_top_k?: number; rerank_top_n?: number; retrieval_mode?: 'auto_routed' | 'chunks' | 'files_via_content' | 'files_via_metadata'; retrieve_image_nodes?: boolean; retrieve_page_figure_nodes?: boolean; retrieve_page_screenshot_nodes?: boolean; search_filters?: { filters: object | metadata_filters[]; condition?: 'and' | 'not' | 'or'; }; search_filters_inference_schema?: object; sparse_similarity_top_k?: number; }`\n - `sparse_model_config?: { class_name?: string; model_type?: 'auto' | 'bm25' | 'splade'; }`\n - `status?: 'CREATED' | 'DELETING'`\n - `transform_config?: { chunk_overlap?: number; chunk_size?: number; mode?: 'auto'; } | { chunking_config?: { mode?: 'none'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'character'; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'token'; separator?: string; } | { chunk_overlap?: number; chunk_size?: number; mode?: 'sentence'; paragraph_separator?: string; separator?: string; } | { breakpoint_percentile_threshold?: number; buffer_size?: number; mode?: 'semantic'; }; mode?: 'advanced'; segmentation_config?: { mode?: 'none'; } | { mode?: 'page'; page_separator?: string; } | { mode?: 'element'; }; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst pipeline = await client.pipelines.dataSources.sync('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', { pipeline_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' });\n\nconsole.log(pipeline);\n```",
|
|
4097
4483
|
perLanguage: {
|
|
4098
4484
|
python: {
|
|
4099
4485
|
method: 'pipelines.data_sources.sync',
|
|
@@ -8073,12 +8459,12 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8073
8459
|
endpoint: '/api/v1/beta/directories/{directory_id}',
|
|
8074
8460
|
httpMethod: 'delete',
|
|
8075
8461
|
summary: 'Delete Directory',
|
|
8076
|
-
description: 'Permanently delete a directory.',
|
|
8462
|
+
description: 'Permanently delete a directory, and the files in it that no other directory or index uses.',
|
|
8077
8463
|
stainlessPath: '(resource) beta.directories > (method) delete',
|
|
8078
8464
|
qualified: 'client.beta.directories.delete',
|
|
8079
8465
|
params: ['directory_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
8080
8466
|
markdown:
|
|
8081
|
-
"## delete\n\n`client.beta.directories.delete(directory_id: string, organization_id?: string, project_id?: string): void`\n\n**delete** `/api/v1/beta/directories/{directory_id}`\n\nPermanently delete a directory.\n\n### Parameters\n\n- `directory_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nawait client.beta.directories.delete('directory_id')\n```",
|
|
8467
|
+
"## delete\n\n`client.beta.directories.delete(directory_id: string, organization_id?: string, project_id?: string): void`\n\n**delete** `/api/v1/beta/directories/{directory_id}`\n\nPermanently delete a directory, and the files in it that no other directory or index uses.\n\n### Parameters\n\n- `directory_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nawait client.beta.directories.delete('directory_id')\n```",
|
|
8082
8468
|
perLanguage: {
|
|
8083
8469
|
python: {
|
|
8084
8470
|
method: 'beta.directories.delete',
|
|
@@ -8361,7 +8747,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8361
8747
|
httpMethod: 'delete',
|
|
8362
8748
|
summary: 'Delete Directory File',
|
|
8363
8749
|
description:
|
|
8364
|
-
'Delete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first.',
|
|
8750
|
+
'Delete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first.\n\nThe uploaded file is deleted with it unless another directory or index still uses it.',
|
|
8365
8751
|
stainlessPath: '(resource) beta.directories.files > (method) delete',
|
|
8366
8752
|
qualified: 'client.beta.directories.files.delete',
|
|
8367
8753
|
params: [
|
|
@@ -8371,7 +8757,7 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8371
8757
|
'project_id?: string;',
|
|
8372
8758
|
],
|
|
8373
8759
|
markdown:
|
|
8374
|
-
"## delete\n\n`client.beta.directories.files.delete(directory_id: string, directory_file_id: string, organization_id?: string, project_id?: string): void`\n\n**delete** `/api/v1/beta/directories/{directory_id}/files/{directory_file_id}`\n\nDelete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first.\n\n### Parameters\n\n- `directory_id: string`\n\n- `directory_file_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nawait client.beta.directories.files.delete('directory_file_id', { directory_id: 'directory_id' })\n```",
|
|
8760
|
+
"## delete\n\n`client.beta.directories.files.delete(directory_id: string, directory_file_id: string, organization_id?: string, project_id?: string): void`\n\n**delete** `/api/v1/beta/directories/{directory_id}/files/{directory_file_id}`\n\nDelete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first.\n\nThe uploaded file is deleted with it unless another directory or index still uses it.\n\n### Parameters\n\n- `directory_id: string`\n\n- `directory_file_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nawait client.beta.directories.files.delete('directory_file_id', { directory_id: 'directory_id' })\n```",
|
|
8375
8761
|
perLanguage: {
|
|
8376
8762
|
python: {
|
|
8377
8763
|
method: 'beta.directories.files.delete',
|
|
@@ -8481,13 +8867,13 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8481
8867
|
'document_input: { type: string; value: string; };',
|
|
8482
8868
|
'organization_id?: string;',
|
|
8483
8869
|
'project_id?: string;',
|
|
8484
|
-
"configuration?: { categories: { name: string; description?: string; }[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; version?: string; };",
|
|
8870
|
+
"configuration?: { categories: { name: string; description?: string; }[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; version?: string; };",
|
|
8485
8871
|
'configuration_id?: string;',
|
|
8486
8872
|
],
|
|
8487
8873
|
response:
|
|
8488
|
-
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8874
|
+
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8489
8875
|
markdown:
|
|
8490
|
-
"## create\n\n`client.beta.split.create(document_input: { type: string; value: string; }, organization_id?: string, project_id?: string, configuration?: { categories: object[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; version?: string; }, configuration_id?: string): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**post** `/api/v1/beta/split/jobs`\n\nCreate a document split job.\n\n### Parameters\n\n- `document_input: { type: string; value: string; }`\n Document to be split.\n - `type: string`\n The beta `POST /api/v1/beta/split/jobs` endpoint accepts only `file_id`. To use a Parse job as input, call `POST /api/v1/split/jobs` instead, where you can pass the Parse job ID as `file_input`.\n - `value: string`\n Document identifier.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { categories: { name: string; description?: string; }[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }; version?: string; }`\n Split configuration with categories and splitting strategy.\n - `categories: { name: string; description?: string; }[]`\n Categories to split documents into.\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; }`\n Strategy for splitting documents.\n - `version?: string`\n Split version to run. Omit for the current release. Preview versions are selectable by name and never resolved automatically.\n\n- `configuration_id?: string`\n Saved split configuration ID.\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.beta.split.create({ document_input: { type: 'type', value: 'value' } });\n\nconsole.log(split);\n```",
|
|
8876
|
+
"## create\n\n`client.beta.split.create(document_input: { type: string; value: string; }, organization_id?: string, project_id?: string, configuration?: { categories: object[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; version?: string; }, configuration_id?: string): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**post** `/api/v1/beta/split/jobs`\n\nCreate a document split job.\n\n### Parameters\n\n- `document_input: { type: string; value: string; }`\n Document to be split.\n - `type: string`\n The beta `POST /api/v1/beta/split/jobs` endpoint accepts only `file_id`. To use a Parse job as input, call `POST /api/v1/split/jobs` instead, where you can pass the Parse job ID as `file_input`.\n - `value: string`\n Document identifier.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { categories: { name: string; description?: string; }[]; splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }; version?: string; }`\n Split configuration with categories and splitting strategy.\n - `categories: { name: string; description?: string; }[]`\n Categories to split documents into. Names must be unique; 'uncategorized' is reserved unless allow_uncategorized is 'forbid'.\n - `splitting_strategy?: { allow_uncategorized?: 'forbid' | 'include' | 'omit'; custom_instructions?: string; min_pages_per_split?: number; segment_boundary?: 'category' | 'document'; }`\n Strategy for splitting documents.\n - `version?: string`\n Split version to run. Omit for the current release. Preview versions are selectable by name and never resolved automatically.\n\n- `configuration_id?: string`\n Saved split configuration ID.\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.beta.split.create({ document_input: { type: 'type', value: 'value' } });\n\nconsole.log(split);\n```",
|
|
8491
8877
|
perLanguage: {
|
|
8492
8878
|
python: {
|
|
8493
8879
|
method: 'beta.split.create',
|
|
@@ -8544,9 +8930,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8544
8930
|
"status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing';",
|
|
8545
8931
|
],
|
|
8546
8932
|
response:
|
|
8547
|
-
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8933
|
+
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8548
8934
|
markdown:
|
|
8549
|
-
"## list\n\n`client.beta.split.list(created_at_on_or_after?: string, created_at_on_or_before?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**get** `/api/v1/beta/split/jobs`\n\nList document split jobs.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'`\n Filter by job status (pending, processing, completed, failed, cancelled)\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const splitListResponse of client.beta.split.list()) {\n console.log(splitListResponse);\n}\n```",
|
|
8935
|
+
"## list\n\n`client.beta.split.list(created_at_on_or_after?: string, created_at_on_or_before?: string, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**get** `/api/v1/beta/split/jobs`\n\nList document split jobs.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n Include items created at or after this timestamp (inclusive)\n\n- `created_at_on_or_before?: string`\n Include items created at or before this timestamp (inclusive)\n\n- `job_ids?: string[]`\n Filter by specific job IDs\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `status?: 'cancelled' | 'completed' | 'failed' | 'pending' | 'processing'`\n Filter by job status (pending, processing, completed, failed, cancelled)\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\n// Automatically fetches more pages as needed.\nfor await (const splitListResponse of client.beta.split.list()) {\n console.log(splitListResponse);\n}\n```",
|
|
8550
8936
|
perLanguage: {
|
|
8551
8937
|
python: {
|
|
8552
8938
|
method: 'beta.split.list',
|
|
@@ -8593,9 +8979,9 @@ const EMBEDDED_METHODS: MethodEntry[] = [
|
|
|
8593
8979
|
qualified: 'client.beta.split.get',
|
|
8594
8980
|
params: ['split_job_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
8595
8981
|
response:
|
|
8596
|
-
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8982
|
+
'{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }',
|
|
8597
8983
|
markdown:
|
|
8598
|
-
"## get\n\n`client.beta.split.get(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**get** `/api/v1/beta/split/jobs/{split_job_id}`\n\nGet a document split job.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.beta.split.get('split_job_id');\n\nconsole.log(split);\n```",
|
|
8984
|
+
"## get\n\n`client.beta.split.get(split_job_id: string, organization_id?: string, project_id?: string): { id: string; categories: split_category[]; document_input: split_document_input; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: split_result_response; updated_at?: string; }`\n\n**get** `/api/v1/beta/split/jobs/{split_job_id}`\n\nGet a document split job.\n\n### Parameters\n\n- `split_job_id: string`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; categories: { name: string; description?: string; }[]; document_input: { type: string; value: string; }; project_id: string; status: string; user_id: string; version: string; configuration_id?: string; created_at?: string; error_message?: string; result?: { segments: split_segment_response[]; }; updated_at?: string; }`\n Beta response — uses nested document_input object.\n\n - `id: string`\n - `categories: { name: string; description?: string; }[]`\n - `document_input: { type: string; value: string; }`\n - `project_id: string`\n - `status: string`\n - `user_id: string`\n - `version: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `result?: { segments: { category: string; confidence_category: string; pages: number[]; }[]; }`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst split = await client.beta.split.get('split_job_id');\n\nconsole.log(split);\n```",
|
|
8599
8985
|
perLanguage: {
|
|
8600
8986
|
python: {
|
|
8601
8987
|
method: 'beta.split.get',
|
|
@@ -8950,12 +9336,12 @@ const EMBEDDED_READMES: { language: string; content: string }[] = [
|
|
|
8950
9336
|
{
|
|
8951
9337
|
language: 'go',
|
|
8952
9338
|
content:
|
|
8953
|
-
'# Llama Cloud Go API Library\n\n<a href="https://pkg.go.dev/github.com/run-llama/llama-parse-go"><img src="https://pkg.go.dev/badge/github.com/run-llama/llama-parse-go.svg" alt="Go Reference"></a>\n\nThe Llama Cloud Go library provides convenient access to the [Llama Cloud REST API](https://developers.llamaindex.ai/)\nfrom applications written in Go.\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## MCP Server\n\nUse the Llama Cloud MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.\n\n[](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBsbGFtYWluZGV4L2xsYW1hLWNsb3VkLW1jcCJdLCJlbnYiOnsiTExBTUFfQ0xPVURfQVBJX0tFWSI6Ik15IEFQSSBLZXkifX0)\n[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40llamaindex%2Fllama-cloud-mcp%22%5D%2C%22env%22%3A%7B%22LLAMA_CLOUD_API_KEY%22%3A%22My%20API%20Key%22%7D%7D)\n\n> Note: You may need to set environment variables in your MCP client.\n\n## Installation\n\n<!-- x-release-please-start-version -->\n\n```go\nimport (\n\t"github.com/run-llama/llama-parse-go" // imported as SDK_PackageName\n)\n```\n\n<!-- x-release-please-end -->\n\nOr to pin the version:\n\n<!-- x-release-please-start-version -->\n\n```sh\ngo get -u \'github.com/run-llama/llama-parse-go@v1.9.0\'\n```\n\n<!-- x-release-please-end -->\n\n## Requirements\n\nThis library requires Go 1.22+.\n\n## Usage\n\nThe full API of this library can be found in [api.md](api.md).\n\n```go\npackage main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"), // defaults to os.LookupEnv("LLAMA_CLOUD_API_KEY")\n\t)\n\tparsing, err := client.Parsing.New(context.TODO(), llamacloud.ParsingNewParams{\n\t\tTier: llamacloud.ParsingNewParamsTierAgentic,\n\t\tVersion: llamacloud.ParsingNewParamsVersionLatest,\n\t\tFileID: llamacloud.String("abc1234"),\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", parsing.ID)\n}\n\n```\n\n### Request fields\n\nAll request parameters are wrapped in a generic `Field` type,\nwhich we use to distinguish zero values from null or omitted fields.\n\nThis prevents accidentally sending a zero value if you forget a required parameter,\nand enables explicitly sending `null`, `false`, `\'\'`, or `0` on optional parameters.\nAny field not specified is not sent.\n\nTo construct fields with values, use the helpers `String()`, `Int()`, `Float()`, or most commonly, the generic `F[T]()`.\nTo send a null, use `Null[T]()`, and to send a nonconforming value, use `Raw[T](any)`. For example:\n\n```go\nparams := FooParams{\n\tName: SDK_PackageName.F("hello"),\n\n\t// Explicitly send `"description": null`\n\tDescription: SDK_PackageName.Null[string](),\n\n\tPoint: SDK_PackageName.F(SDK_PackageName.Point{\n\t\tX: SDK_PackageName.Int(0),\n\t\tY: SDK_PackageName.Int(1),\n\n\t\t// In cases where the API specifies a given type,\n\t\t// but you want to send something else, use `Raw`:\n\t\tZ: SDK_PackageName.Raw[int64](0.01), // sends a float\n\t}),\n}\n```\n\n### Response objects\n\nAll fields in response structs are value types (not pointers or wrappers).\n\nIf a given field is `null`, not present, or invalid, the corresponding field\nwill simply be its zero value.\n\nAll response structs also include a special `JSON` field, containing more detailed\ninformation about each property, which you can use like so:\n\n```go\nif res.Name == "" {\n\t// true if `"name"` is either not present or explicitly null\n\tres.JSON.Name.IsNull()\n\n\t// true if the `"name"` key was not present in the response JSON at all\n\tres.JSON.Name.IsMissing()\n\n\t// When the API returns data that cannot be coerced to the expected type:\n\tif res.JSON.Name.IsInvalid() {\n\t\traw := res.JSON.Name.Raw()\n\n\t\tlegacyName := struct{\n\t\t\tFirst string `json:"first"`\n\t\t\tLast string `json:"last"`\n\t\t}{}\n\t\tjson.Unmarshal([]byte(raw), &legacyName)\n\t\tname = legacyName.First + " " + legacyName.Last\n\t}\n}\n```\n\nThese `.JSON` structs also include an `Extras` map containing\nany properties in the json response that were not specified\nin the struct. This can be useful for API features not yet\npresent in the SDK.\n\n```go\nbody := res.JSON.ExtraFields["my_unexpected_field"].Raw()\n```\n\n### RequestOptions\n\nThis library uses the functional options pattern. Functions defined in the\n`SDK_PackageOptionName` package return a `RequestOption`, which is a closure that mutates a\n`RequestConfig`. These options can be supplied to the client or at individual\nrequests. For example:\n\n```go\nclient := SDK_PackageName.SDK_ClientInitializerName(\n\t// Adds a header to every request made by the client\n\tSDK_PackageOptionName.WithHeader("X-Some-Header", "custom_header_info"),\n)\n\nclient.Indexes.List(context.TODO(), ...,\n\t// Override the header\n\tSDK_PackageOptionName.WithHeader("X-Some-Header", "some_other_custom_header_info"),\n\t// Add an undocumented field to the request body, using sjson syntax\n\tSDK_PackageOptionName.WithJSONSet("some.json.path", map[string]string{"my": "object"}),\n)\n```\n\nSee the [full list of request options](https://pkg.go.dev/github.com/run-llama/llama-parse-go/SDK_PackageOptionName).\n\n### Pagination\n\nThis library provides some conveniences for working with paginated list endpoints.\n\nYou can use `.ListAutoPaging()` methods to iterate through items across all pages:\n\n```go\niter := client.Extract.ListAutoPaging(context.TODO(), llamacloud.ExtractListParams{\n\tPageSize: llamacloud.Int(20),\n})\n// Automatically fetches more pages as needed.\nfor iter.Next() {\n\textractV2Job := iter.Current()\n\tfmt.Printf("%+v\\n", extractV2Job)\n}\nif err := iter.Err(); err != nil {\n\tpanic(err.Error())\n}\n```\n\nOr you can use simple `.List()` methods to fetch a single page and receive a standard response object\nwith additional helper methods like `.GetNextPage()`, e.g.:\n\n```go\npage, err := client.Extract.List(context.TODO(), llamacloud.ExtractListParams{\n\tPageSize: llamacloud.Int(20),\n})\nfor page != nil {\n\tfor _, extract := range page.Items {\n\t\tfmt.Printf("%+v\\n", extract)\n\t}\n\tpage, err = page.GetNextPage()\n}\nif err != nil {\n\tpanic(err.Error())\n}\n```\n\n### Errors\n\nWhen the API returns a non-success status code, we return an error with type\n`*SDK_PackageName.Error`. This contains the `StatusCode`, `*http.Request`, and\n`*http.Response` values of the request, as well as the JSON of the error body\n(much like other response objects in the SDK).\n\nTo handle errors, we recommend that you use the `errors.As` pattern:\n\n```go\n_, err := client.Indexes.List(context.TODO(), llamacloud.IndexListParams{\n\tProjectID: llamacloud.String("my-project-id"),\n})\nif err != nil {\n\tvar apierr *llamacloud.Error\n\tif errors.As(err, &apierr) {\n\t\tprintln(string(apierr.DumpRequest(true))) // Prints the serialized HTTP request\n\t\tprintln(string(apierr.DumpResponse(true))) // Prints the serialized HTTP response\n\t}\n\tpanic(err.Error()) // GET "/api/v1/indexes": 400 Bad Request { ... }\n}\n```\n\nWhen other errors occur, they are returned unwrapped; for example,\nif HTTP transport fails, you might receive `*url.Error` wrapping `*net.OpError`.\n\n### Timeouts\n\nRequests do not time out by default; use context to configure a timeout for a request lifecycle.\n\nNote that if a request is [retried](#retries), the context timeout does not start over.\nTo set a per-retry timeout, use `SDK_PackageOptionName.WithRequestTimeout()`.\n\n```go\n// This sets the timeout for the request, including all the retries.\nctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)\ndefer cancel()\nclient.Indexes.List(\n\tctx,\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\t// This sets the per-retry timeout\n\toption.WithRequestTimeout(20*time.Second),\n)\n```\n\n### File uploads\n\nRequest parameters that correspond to file uploads in multipart requests are typed as\n`param.Field[io.Reader]`. The contents of the `io.Reader` will by default be sent as a multipart form\npart with the file name of "anonymous_file" and content-type of "application/octet-stream".\n\nThe file name and content-type can be customized by implementing `Name() string` or `ContentType()\nstring` on the run-time type of `io.Reader`. Note that `os.File` implements `Name() string`, so a\nfile returned by `os.Open` will be sent with the file name on disk.\n\nWe also provide a helper `SDK_PackageName.FileParam(reader io.Reader, filename string, contentType string)`\nwhich can be used to wrap any `io.Reader` with the appropriate file name and content type.\n\n```go\n// A file from the file system\nfile, err := os.Open("/path/to/file")\nllamacloud.FileNewParams{\n\tFile: file,\n\tPurpose: "purpose",\n}\n\n// A file from a string\nllamacloud.FileNewParams{\n\tFile: strings.NewReader("my file contents"),\n\tPurpose: "purpose",\n}\n\n// With a custom filename and contentType\nllamacloud.FileNewParams{\n\tFile: llamacloud.File(strings.NewReader(`{"hello": "foo"}`), "file.go", "application/json"),\n\tPurpose: "purpose",\n}\n```\n\n### Retries\n\nCertain errors will be automatically retried 2 times by default, with a short exponential backoff.\nWe retry by default all connection errors, 408 Request Timeout, 409 Conflict, 429 Rate Limit,\nand >=500 Internal errors.\n\nYou can use the `WithMaxRetries` option to configure or disable this:\n\n```go\n// Configure the default for all requests:\nclient := llamacloud.NewClient(\n\toption.WithMaxRetries(0), // default is 2\n)\n\n// Override per-request:\nclient.Indexes.List(\n\tcontext.TODO(),\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\toption.WithMaxRetries(5),\n)\n```\n\n\n### Accessing raw response data (e.g. response headers)\n\nYou can access the raw HTTP response data by using the `option.WithResponseInto()` request option. This is useful when\nyou need to examine response headers, status codes, or other details.\n\n```go\n// Create a variable to store the HTTP response\nvar response *http.Response\npage, err := client.Indexes.List(\n\tcontext.TODO(),\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\toption.WithResponseInto(&response),\n)\nif err != nil {\n\t// handle error\n}\nfmt.Printf("%+v\\n", page)\n\nfmt.Printf("Status Code: %d\\n", response.StatusCode)\nfmt.Printf("Headers: %+#v\\n", response.Header)\n```\n\n### Making custom/undocumented requests\n\nThis library is typed for convenient access to the documented API. If you need to access undocumented\nendpoints, params, or response properties, the library can still be used.\n\n#### Undocumented endpoints\n\nTo make requests to undocumented endpoints, you can use `client.Get`, `client.Post`, and other HTTP verbs.\n`RequestOptions` on the client, such as retries, will be respected when making these requests.\n\n```go\nvar (\n // params can be an io.Reader, a []byte, an encoding/json serializable object,\n // or a "…Params" struct defined in this library.\n params map[string]interface{}\n\n // result can be an []byte, *http.Response, a encoding/json deserializable object,\n // or a model defined in this library.\n result *http.Response\n)\nerr := client.Post(context.Background(), "/unspecified", params, &result)\nif err != nil {\n …\n}\n```\n\n#### Undocumented request params\n\nTo make requests using undocumented parameters, you may use either the `SDK_PackageOptionName.WithQuerySet()`\nor the `SDK_PackageOptionName.WithJSONSet()` methods.\n\n```go\nparams := FooNewParams{\n ID: SDK_PackageName.F("id_xxxx"),\n Data: SDK_PackageName.F(FooNewParamsData{\n FirstName: SDK_PackageName.F("John"),\n }),\n}\nclient.Foo.New(context.Background(), params, SDK_PackageOptionName.WithJSONSet("data.last_name", "Doe"))\n```\n\n#### Undocumented response properties\n\nTo access undocumented response properties, you may either access the raw JSON of the response as a string\nwith `result.JSON.RawJSON()`, or get the raw JSON of a particular field on the result with\n`result.JSON.Foo.Raw()`.\n\nAny fields that are not present on the response struct will be saved and can be accessed by `result.JSON.ExtraFields()` which returns the extra fields as a `map[string]Field`.\n\n### Middleware\n\nWe provide `SDK_PackageOptionName.WithMiddleware` which applies the given\nmiddleware to requests.\n\n```go\nfunc Logger(req *http.Request, next SDK_PackageOptionName.MiddlewareNext) (res *http.Response, err error) {\n\t// Before the request\n\tstart := time.Now()\n\tLogReq(req)\n\n\t// Forward the request to the next handler\n\tres, err = next(req)\n\n\t// Handle stuff after the request\n\tend := time.Now()\n\tLogRes(res, err, start - end)\n\n return res, err\n}\n\nclient := SDK_PackageName.SDK_ClientInitializerName(\n\tSDK_PackageOptionName.WithMiddleware(Logger),\n)\n```\n\nWhen multiple middlewares are provided as variadic arguments, the middlewares\nare applied left to right. If `SDK_PackageOptionName.WithMiddleware` is given\nmultiple times, for example first in the client then the method, the\nmiddleware in the client will run first and the middleware given in the method\nwill run next.\n\nYou may also replace the default `http.Client` with\n`SDK_PackageOptionName.WithHTTPClient(client)`. Only one http client is\naccepted (this overwrites any previous client) and receives requests after any\nmiddleware has been applied.\n\n## Semantic versioning\n\nThis package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:\n\n1. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_\n2. Changes that we do not expect to impact the vast majority of users in practice.\n\nWe take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.\n\nWe are keen for your feedback; please open an [issue](https://www.github.com/run-llama/llama-parse-go/issues) with questions, bugs, or suggestions.\n\n## Contributing\n\nSee [the contributing documentation](./CONTRIBUTING.md).\n',
|
|
9339
|
+
'# Llama Cloud Go API Library\n\n<a href="https://pkg.go.dev/github.com/run-llama/llama-parse-go"><img src="https://pkg.go.dev/badge/github.com/run-llama/llama-parse-go.svg" alt="Go Reference"></a>\n\nThe Llama Cloud Go library provides convenient access to the [Llama Cloud REST API](https://developers.llamaindex.ai/)\nfrom applications written in Go.\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## MCP Server\n\nUse the Llama Cloud MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.\n\n[](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBsbGFtYWluZGV4L2xsYW1hLWNsb3VkLW1jcCJdLCJlbnYiOnsiTExBTUFfQ0xPVURfQVBJX0tFWSI6Ik15IEFQSSBLZXkifX0)\n[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40llamaindex%2Fllama-cloud-mcp%22%5D%2C%22env%22%3A%7B%22LLAMA_CLOUD_API_KEY%22%3A%22My%20API%20Key%22%7D%7D)\n\n> Note: You may need to set environment variables in your MCP client.\n\n## Installation\n\n<!-- x-release-please-start-version -->\n\n```go\nimport (\n\t"github.com/run-llama/llama-parse-go" // imported as SDK_PackageName\n)\n```\n\n<!-- x-release-please-end -->\n\nOr to pin the version:\n\n<!-- x-release-please-start-version -->\n\n```sh\ngo get -u \'github.com/run-llama/llama-parse-go@v1.10.0\'\n```\n\n<!-- x-release-please-end -->\n\n## Requirements\n\nThis library requires Go 1.22+.\n\n## Usage\n\nThe full API of this library can be found in [api.md](api.md).\n\n```go\npackage main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/run-llama/llama-parse-go"\n\t"github.com/run-llama/llama-parse-go/option"\n)\n\nfunc main() {\n\tclient := llamacloud.NewClient(\n\t\toption.WithAPIKey("My API Key"), // defaults to os.LookupEnv("LLAMA_CLOUD_API_KEY")\n\t)\n\tparsing, err := client.Parsing.New(context.TODO(), llamacloud.ParsingNewParams{\n\t\tTier: llamacloud.ParsingNewParamsTierAgentic,\n\t\tVersion: llamacloud.ParsingNewParamsVersionLatest,\n\t\tFileID: llamacloud.String("abc1234"),\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", parsing.ID)\n}\n\n```\n\n### Request fields\n\nAll request parameters are wrapped in a generic `Field` type,\nwhich we use to distinguish zero values from null or omitted fields.\n\nThis prevents accidentally sending a zero value if you forget a required parameter,\nand enables explicitly sending `null`, `false`, `\'\'`, or `0` on optional parameters.\nAny field not specified is not sent.\n\nTo construct fields with values, use the helpers `String()`, `Int()`, `Float()`, or most commonly, the generic `F[T]()`.\nTo send a null, use `Null[T]()`, and to send a nonconforming value, use `Raw[T](any)`. For example:\n\n```go\nparams := FooParams{\n\tName: SDK_PackageName.F("hello"),\n\n\t// Explicitly send `"description": null`\n\tDescription: SDK_PackageName.Null[string](),\n\n\tPoint: SDK_PackageName.F(SDK_PackageName.Point{\n\t\tX: SDK_PackageName.Int(0),\n\t\tY: SDK_PackageName.Int(1),\n\n\t\t// In cases where the API specifies a given type,\n\t\t// but you want to send something else, use `Raw`:\n\t\tZ: SDK_PackageName.Raw[int64](0.01), // sends a float\n\t}),\n}\n```\n\n### Response objects\n\nAll fields in response structs are value types (not pointers or wrappers).\n\nIf a given field is `null`, not present, or invalid, the corresponding field\nwill simply be its zero value.\n\nAll response structs also include a special `JSON` field, containing more detailed\ninformation about each property, which you can use like so:\n\n```go\nif res.Name == "" {\n\t// true if `"name"` is either not present or explicitly null\n\tres.JSON.Name.IsNull()\n\n\t// true if the `"name"` key was not present in the response JSON at all\n\tres.JSON.Name.IsMissing()\n\n\t// When the API returns data that cannot be coerced to the expected type:\n\tif res.JSON.Name.IsInvalid() {\n\t\traw := res.JSON.Name.Raw()\n\n\t\tlegacyName := struct{\n\t\t\tFirst string `json:"first"`\n\t\t\tLast string `json:"last"`\n\t\t}{}\n\t\tjson.Unmarshal([]byte(raw), &legacyName)\n\t\tname = legacyName.First + " " + legacyName.Last\n\t}\n}\n```\n\nThese `.JSON` structs also include an `Extras` map containing\nany properties in the json response that were not specified\nin the struct. This can be useful for API features not yet\npresent in the SDK.\n\n```go\nbody := res.JSON.ExtraFields["my_unexpected_field"].Raw()\n```\n\n### RequestOptions\n\nThis library uses the functional options pattern. Functions defined in the\n`SDK_PackageOptionName` package return a `RequestOption`, which is a closure that mutates a\n`RequestConfig`. These options can be supplied to the client or at individual\nrequests. For example:\n\n```go\nclient := SDK_PackageName.SDK_ClientInitializerName(\n\t// Adds a header to every request made by the client\n\tSDK_PackageOptionName.WithHeader("X-Some-Header", "custom_header_info"),\n)\n\nclient.Indexes.List(context.TODO(), ...,\n\t// Override the header\n\tSDK_PackageOptionName.WithHeader("X-Some-Header", "some_other_custom_header_info"),\n\t// Add an undocumented field to the request body, using sjson syntax\n\tSDK_PackageOptionName.WithJSONSet("some.json.path", map[string]string{"my": "object"}),\n)\n```\n\nSee the [full list of request options](https://pkg.go.dev/github.com/run-llama/llama-parse-go/SDK_PackageOptionName).\n\n### Pagination\n\nThis library provides some conveniences for working with paginated list endpoints.\n\nYou can use `.ListAutoPaging()` methods to iterate through items across all pages:\n\n```go\niter := client.Extract.ListAutoPaging(context.TODO(), llamacloud.ExtractListParams{\n\tPageSize: llamacloud.Int(20),\n})\n// Automatically fetches more pages as needed.\nfor iter.Next() {\n\textractV2Job := iter.Current()\n\tfmt.Printf("%+v\\n", extractV2Job)\n}\nif err := iter.Err(); err != nil {\n\tpanic(err.Error())\n}\n```\n\nOr you can use simple `.List()` methods to fetch a single page and receive a standard response object\nwith additional helper methods like `.GetNextPage()`, e.g.:\n\n```go\npage, err := client.Extract.List(context.TODO(), llamacloud.ExtractListParams{\n\tPageSize: llamacloud.Int(20),\n})\nfor page != nil {\n\tfor _, extract := range page.Items {\n\t\tfmt.Printf("%+v\\n", extract)\n\t}\n\tpage, err = page.GetNextPage()\n}\nif err != nil {\n\tpanic(err.Error())\n}\n```\n\n### Errors\n\nWhen the API returns a non-success status code, we return an error with type\n`*SDK_PackageName.Error`. This contains the `StatusCode`, `*http.Request`, and\n`*http.Response` values of the request, as well as the JSON of the error body\n(much like other response objects in the SDK).\n\nTo handle errors, we recommend that you use the `errors.As` pattern:\n\n```go\n_, err := client.Indexes.List(context.TODO(), llamacloud.IndexListParams{\n\tProjectID: llamacloud.String("my-project-id"),\n})\nif err != nil {\n\tvar apierr *llamacloud.Error\n\tif errors.As(err, &apierr) {\n\t\tprintln(string(apierr.DumpRequest(true))) // Prints the serialized HTTP request\n\t\tprintln(string(apierr.DumpResponse(true))) // Prints the serialized HTTP response\n\t}\n\tpanic(err.Error()) // GET "/api/v1/indexes": 400 Bad Request { ... }\n}\n```\n\nWhen other errors occur, they are returned unwrapped; for example,\nif HTTP transport fails, you might receive `*url.Error` wrapping `*net.OpError`.\n\n### Timeouts\n\nRequests do not time out by default; use context to configure a timeout for a request lifecycle.\n\nNote that if a request is [retried](#retries), the context timeout does not start over.\nTo set a per-retry timeout, use `SDK_PackageOptionName.WithRequestTimeout()`.\n\n```go\n// This sets the timeout for the request, including all the retries.\nctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)\ndefer cancel()\nclient.Indexes.List(\n\tctx,\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\t// This sets the per-retry timeout\n\toption.WithRequestTimeout(20*time.Second),\n)\n```\n\n### File uploads\n\nRequest parameters that correspond to file uploads in multipart requests are typed as\n`param.Field[io.Reader]`. The contents of the `io.Reader` will by default be sent as a multipart form\npart with the file name of "anonymous_file" and content-type of "application/octet-stream".\n\nThe file name and content-type can be customized by implementing `Name() string` or `ContentType()\nstring` on the run-time type of `io.Reader`. Note that `os.File` implements `Name() string`, so a\nfile returned by `os.Open` will be sent with the file name on disk.\n\nWe also provide a helper `SDK_PackageName.FileParam(reader io.Reader, filename string, contentType string)`\nwhich can be used to wrap any `io.Reader` with the appropriate file name and content type.\n\n```go\n// A file from the file system\nfile, err := os.Open("/path/to/file")\nllamacloud.FileNewParams{\n\tFile: file,\n\tPurpose: "purpose",\n}\n\n// A file from a string\nllamacloud.FileNewParams{\n\tFile: strings.NewReader("my file contents"),\n\tPurpose: "purpose",\n}\n\n// With a custom filename and contentType\nllamacloud.FileNewParams{\n\tFile: llamacloud.File(strings.NewReader(`{"hello": "foo"}`), "file.go", "application/json"),\n\tPurpose: "purpose",\n}\n```\n\n### Retries\n\nCertain errors will be automatically retried 2 times by default, with a short exponential backoff.\nWe retry by default all connection errors, 408 Request Timeout, 409 Conflict, 429 Rate Limit,\nand >=500 Internal errors.\n\nYou can use the `WithMaxRetries` option to configure or disable this:\n\n```go\n// Configure the default for all requests:\nclient := llamacloud.NewClient(\n\toption.WithMaxRetries(0), // default is 2\n)\n\n// Override per-request:\nclient.Indexes.List(\n\tcontext.TODO(),\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\toption.WithMaxRetries(5),\n)\n```\n\n\n### Accessing raw response data (e.g. response headers)\n\nYou can access the raw HTTP response data by using the `option.WithResponseInto()` request option. This is useful when\nyou need to examine response headers, status codes, or other details.\n\n```go\n// Create a variable to store the HTTP response\nvar response *http.Response\npage, err := client.Indexes.List(\n\tcontext.TODO(),\n\tllamacloud.IndexListParams{\n\t\tProjectID: llamacloud.String("my-project-id"),\n\t},\n\toption.WithResponseInto(&response),\n)\nif err != nil {\n\t// handle error\n}\nfmt.Printf("%+v\\n", page)\n\nfmt.Printf("Status Code: %d\\n", response.StatusCode)\nfmt.Printf("Headers: %+#v\\n", response.Header)\n```\n\n### Making custom/undocumented requests\n\nThis library is typed for convenient access to the documented API. If you need to access undocumented\nendpoints, params, or response properties, the library can still be used.\n\n#### Undocumented endpoints\n\nTo make requests to undocumented endpoints, you can use `client.Get`, `client.Post`, and other HTTP verbs.\n`RequestOptions` on the client, such as retries, will be respected when making these requests.\n\n```go\nvar (\n // params can be an io.Reader, a []byte, an encoding/json serializable object,\n // or a "…Params" struct defined in this library.\n params map[string]interface{}\n\n // result can be an []byte, *http.Response, a encoding/json deserializable object,\n // or a model defined in this library.\n result *http.Response\n)\nerr := client.Post(context.Background(), "/unspecified", params, &result)\nif err != nil {\n …\n}\n```\n\n#### Undocumented request params\n\nTo make requests using undocumented parameters, you may use either the `SDK_PackageOptionName.WithQuerySet()`\nor the `SDK_PackageOptionName.WithJSONSet()` methods.\n\n```go\nparams := FooNewParams{\n ID: SDK_PackageName.F("id_xxxx"),\n Data: SDK_PackageName.F(FooNewParamsData{\n FirstName: SDK_PackageName.F("John"),\n }),\n}\nclient.Foo.New(context.Background(), params, SDK_PackageOptionName.WithJSONSet("data.last_name", "Doe"))\n```\n\n#### Undocumented response properties\n\nTo access undocumented response properties, you may either access the raw JSON of the response as a string\nwith `result.JSON.RawJSON()`, or get the raw JSON of a particular field on the result with\n`result.JSON.Foo.Raw()`.\n\nAny fields that are not present on the response struct will be saved and can be accessed by `result.JSON.ExtraFields()` which returns the extra fields as a `map[string]Field`.\n\n### Middleware\n\nWe provide `SDK_PackageOptionName.WithMiddleware` which applies the given\nmiddleware to requests.\n\n```go\nfunc Logger(req *http.Request, next SDK_PackageOptionName.MiddlewareNext) (res *http.Response, err error) {\n\t// Before the request\n\tstart := time.Now()\n\tLogReq(req)\n\n\t// Forward the request to the next handler\n\tres, err = next(req)\n\n\t// Handle stuff after the request\n\tend := time.Now()\n\tLogRes(res, err, start - end)\n\n return res, err\n}\n\nclient := SDK_PackageName.SDK_ClientInitializerName(\n\tSDK_PackageOptionName.WithMiddleware(Logger),\n)\n```\n\nWhen multiple middlewares are provided as variadic arguments, the middlewares\nare applied left to right. If `SDK_PackageOptionName.WithMiddleware` is given\nmultiple times, for example first in the client then the method, the\nmiddleware in the client will run first and the middleware given in the method\nwill run next.\n\nYou may also replace the default `http.Client` with\n`SDK_PackageOptionName.WithHTTPClient(client)`. Only one http client is\naccepted (this overwrites any previous client) and receives requests after any\nmiddleware has been applied.\n\n## Semantic versioning\n\nThis package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:\n\n1. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_\n2. Changes that we do not expect to impact the vast majority of users in practice.\n\nWe take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.\n\nWe are keen for your feedback; please open an [issue](https://www.github.com/run-llama/llama-parse-go/issues) with questions, bugs, or suggestions.\n\n## Contributing\n\nSee [the contributing documentation](./CONTRIBUTING.md).\n',
|
|
8954
9340
|
},
|
|
8955
9341
|
{
|
|
8956
9342
|
language: 'java',
|
|
8957
9343
|
content:
|
|
8958
|
-
'# Llama Cloud Java API Library\n\n<!-- x-release-please-start-version -->\n[](https://central.sonatype.com/artifact/ai.llamaindex.llamacloud/llama-cloud/1.9.0)\n[](https://javadoc.io/doc/ai.llamaindex.llamacloud/llama-cloud/1.9.0)\n<!-- x-release-please-end -->\n\nThe Llama Cloud Java SDK provides convenient access to the [Llama Cloud REST API](https://developers.llamaindex.ai/) from applications written in Java.\n\n\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## MCP Server\n\nUse the Llama Cloud MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.\n\n[](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBsbGFtYWluZGV4L2xsYW1hLWNsb3VkLW1jcCJdLCJlbnYiOnsiTExBTUFfQ0xPVURfQVBJX0tFWSI6Ik15IEFQSSBLZXkifX0)\n[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40llamaindex%2Fllama-cloud-mcp%22%5D%2C%22env%22%3A%7B%22LLAMA_CLOUD_API_KEY%22%3A%22My%20API%20Key%22%7D%7D)\n\n> Note: You may need to set environment variables in your MCP client.\n\n<!-- x-release-please-start-version -->\n\nThe REST API documentation can be found on [developers.llamaindex.ai](https://developers.llamaindex.ai/). Javadocs are available on [javadoc.io](https://javadoc.io/doc/ai.llamaindex.llamacloud/llama-cloud/1.9.0).\n\n<!-- x-release-please-end -->\n\n## Installation\n\n<!-- x-release-please-start-version -->\n\n### Gradle\n\n~~~kotlin\nimplementation("ai.llamaindex:llama-cloud:1.9.0")\n~~~\n\n### Maven\n\n~~~xml\n<dependency>\n <groupId>ai.llamaindex</groupId>\n <artifactId>llama-cloud</artifactId>\n <version>1.9.0</version>\n</dependency>\n~~~\n\n<!-- x-release-please-end -->\n\n## Requirements\n\nThis library requires Java 8 or later.\n\n## Usage\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nParsingCreateResponse parsing = client.parsing().create(params);\n```\n\n## Client configuration\n\nConfigure the client using system properties or environment variables:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n```\n\nOr manually:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .apiKey("My API Key")\n .build();\n```\n\nOr using a combination of the two approaches:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n // Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n // Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\n .fromEnv()\n .apiKey("My API Key")\n .build();\n```\n\nSee this table for the available options:\n\n| Setter | System property | Environment variable | Required | Default value |\n| --------- | -------------------- | ---------------------- | -------- | ----------------------------------- |\n| `apiKey` | `llamacloud.apiKey` | `LLAMA_CLOUD_API_KEY` | true | - |\n| `baseUrl` | `llamacloud.baseUrl` | `LLAMA_CLOUD_BASE_URL` | true | `"https://api.cloud.llamaindex.ai"` |\n\nSystem properties take precedence over environment variables.\n\n> [!TIP]\n> Don\'t create more than one client in the same application. Each client has a connection pool and\n> thread pools, which are more efficient to share between requests.\n\n### Modifying configuration\n\nTo temporarily use a modified client configuration, while reusing the same connection and thread pools, call `withOptions()` on any client or service:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\n\nLlamaCloudClient clientWithOptions = client.withOptions(optionsBuilder -> {\n optionsBuilder.baseUrl("https://example.com");\n optionsBuilder.maxRetries(42);\n});\n```\n\nThe `withOptions()` method does not affect the original client or service.\n\n## Requests and responses\n\nTo send a request to the Llama Cloud API, build an instance of some `Params` class and pass it to the corresponding client method. When the response is received, it will be deserialized into an instance of a Java class.\n\nFor example, `client.parsing().create(...)` should be called with an instance of `ParsingCreateParams`, and it will return an instance of `ParsingCreateResponse`.\n\n## Immutability\n\nEach class in the SDK has an associated [builder](https://blogs.oracle.com/javamagazine/post/exploring-joshua-blochs-builder-design-pattern-in-java) or factory method for constructing it.\n\nEach class is [immutable](https://docs.oracle.com/javase/tutorial/essential/concurrency/immutable.html) once constructed. If the class has an associated builder, then it has a `toBuilder()` method, which can be used to convert it back to a builder for making a modified copy.\n\nBecause each class is immutable, builder modification will _never_ affect already built class instances.\n\n## Asynchronous execution\n\nThe default client is synchronous. To switch to asynchronous execution, call the `async()` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\nimport java.util.concurrent.CompletableFuture;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nCompletableFuture<ParsingCreateResponse> parsing = client.async().parsing().create(params);\n```\n\nOr create an asynchronous client from the beginning:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClientAsync;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClientAsync;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\nimport java.util.concurrent.CompletableFuture;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClientAsync client = LlamaCloudOkHttpClientAsync.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nCompletableFuture<ParsingCreateResponse> parsing = client.parsing().create(params);\n```\n\nThe asynchronous client supports the same options as the synchronous one, except most methods return `CompletableFuture`s.\n\n\n\n## File uploads\n\nThe SDK defines methods that accept files.\n\nTo upload a file, pass a [`Path`](https://docs.oracle.com/javase/8/docs/api/java/nio/file/Path.html):\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.nio.file.Paths;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(Paths.get("/path/to/file"))\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nOr an arbitrary [`InputStream`](https://docs.oracle.com/javase/8/docs/api/java/io/InputStream.html):\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.net.URL;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(new URL("https://example.com//path/to/file").openStream())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nOr a `byte[]` array:\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file("content".getBytes())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nNote that when passing a non-`Path` its filename is unknown so it will not be included in the request. To manually set a filename, pass a [`MultipartField`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.MultipartField;\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.io.InputStream;\nimport java.net.URL;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(MultipartField.<InputStream>builder()\n .value(new URL("https://example.com//path/to/file").openStream())\n .filename("/path/to/file")\n .build())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\n\n\n## Raw responses\n\nThe SDK defines methods that deserialize responses into instances of Java classes. However, these methods don\'t provide access to the response headers, status code, or the raw response body.\n\nTo access this data, prefix any HTTP method call on a client or service with `withRawResponse()`:\n\n```java\nimport ai.llamaindex.llamacloud.core.http.Headers;\nimport ai.llamaindex.llamacloud.core.http.HttpResponseFor;\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\nimport ai.llamaindex.llamacloud.models.indexes.IndexListParams;\n\nIndexListParams params = IndexListParams.builder()\n .projectId("my-project-id")\n .build();\nHttpResponseFor<IndexListPage> page = client.indexes().withRawResponse().list(params);\n\nint statusCode = page.statusCode();\nHeaders headers = page.headers();\n```\n\nYou can still deserialize the response into an instance of a Java class if needed:\n\n```java\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\n\nIndexListPage parsedPage = page.parse();\n```\n\n## Error handling\n\nThe SDK throws custom unchecked exception types:\n\n- [`LlamaCloudServiceException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudServiceException.kt): Base class for HTTP errors. See this table for which exception subclass is thrown for each HTTP status code:\n\n | Status | Exception |\n | ------ | -------------------------------------------------- |\n | 400 | [`BadRequestException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/BadRequestException.kt) |\n | 401 | [`UnauthorizedException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnauthorizedException.kt) |\n | 403 | [`PermissionDeniedException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/PermissionDeniedException.kt) |\n | 404 | [`NotFoundException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/NotFoundException.kt) |\n | 422 | [`UnprocessableEntityException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnprocessableEntityException.kt) |\n | 429 | [`RateLimitException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/RateLimitException.kt) |\n | 5xx | [`InternalServerException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/InternalServerException.kt) |\n | others | [`UnexpectedStatusCodeException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnexpectedStatusCodeException.kt) |\n\n- [`LlamaCloudIoException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudIoException.kt): I/O networking errors.\n\n- [`LlamaCloudRetryableException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudRetryableException.kt): Generic error indicating a failure that could be retried by the client.\n\n- [`LlamaCloudInvalidDataException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudInvalidDataException.kt): Failure to interpret successfully parsed data. For example, when accessing a property that\'s supposed to be required, but the API unexpectedly omitted it from the response.\n\n- [`LlamaCloudException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudException.kt): Base class for all exceptions. Most errors will result in one of the previously mentioned ones, but completely generic errors may be thrown using the base class.\n\n## Pagination\n\nThe SDK defines methods that return a paginated lists of results. It provides convenient ways to access the results either one page at a time or item-by-item across all pages.\n\n### Auto-pagination\n\nTo iterate through all results across all pages, use the `autoPager()` method, which automatically fetches more pages as needed.\n\nWhen using the synchronous client, the method returns an [`Iterable`](https://docs.oracle.com/javase/8/docs/api/java/lang/Iterable.html)\n\n```java\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPage;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\n\nExtractListPage page = client.extract().list();\n\n// Process as an Iterable\nfor (ExtractV2Job extract : page.autoPager()) {\n System.out.println(extract);\n}\n\n// Process as a Stream\npage.autoPager()\n .stream()\n .limit(50)\n .forEach(extract -> System.out.println(extract));\n```\n\nWhen using the asynchronous client, the method returns an [`AsyncStreamResponse`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/http/AsyncStreamResponse.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.http.AsyncStreamResponse;\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPageAsync;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\nimport java.util.Optional;\nimport java.util.concurrent.CompletableFuture;\n\nCompletableFuture<ExtractListPageAsync> pageFuture = client.async().extract().list();\n\npageFuture.thenRun(page -> page.autoPager().subscribe(extract -> {\n System.out.println(extract);\n}));\n\n// If you need to handle errors or completion of the stream\npageFuture.thenRun(page -> page.autoPager().subscribe(new AsyncStreamResponse.Handler<>() {\n @Override\n public void onNext(ExtractV2Job extract) {\n System.out.println(extract);\n }\n\n @Override\n public void onComplete(Optional<Throwable> error) {\n if (error.isPresent()) {\n System.out.println("Something went wrong!");\n throw new RuntimeException(error.get());\n } else {\n System.out.println("No more!");\n }\n }\n}));\n\n// Or use futures\npageFuture.thenRun(page -> page.autoPager()\n .subscribe(extract -> {\n System.out.println(extract);\n })\n .onCompleteFuture()\n .whenComplete((unused, error) -> {\n if (error != null) {\n System.out.println("Something went wrong!");\n throw new RuntimeException(error);\n } else {\n System.out.println("No more!");\n }\n }));\n```\n\n### Manual pagination\n\nTo access individual page items and manually request the next page, use the `items()`,\n`hasNextPage()`, and `nextPage()` methods:\n\n```java\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPage;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\n\nExtractListPage page = client.extract().list();\nwhile (true) {\n for (ExtractV2Job extract : page.items()) {\n System.out.println(extract);\n }\n\n if (!page.hasNextPage()) {\n break;\n }\n\n page = page.nextPage();\n}\n```\n\n## Logging\n\nEnable logging by setting the `LLAMA_CLOUD_LOG` environment variable to `info`:\n\n```sh\nexport LLAMA_CLOUD_LOG=info\n```\n\nOr to `debug` for more verbose logging:\n\n```sh\nexport LLAMA_CLOUD_LOG=debug\n```\n\nOr configure the client manually using the `logLevel` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.core.LogLevel;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .logLevel(LogLevel.INFO)\n .build();\n```\n\n## ProGuard and R8\n\nAlthough the SDK uses reflection, it is still usable with [ProGuard](https://github.com/Guardsquare/proguard) and [R8](https://developer.android.com/topic/performance/app-optimization/enable-app-optimization) because `llama-cloud-core` is published with a [configuration file](llama-cloud-core/src/main/resources/META-INF/proguard/llama-cloud-core.pro) containing [keep rules](https://www.guardsquare.com/manual/configuration/usage).\n\nProGuard and R8 should automatically detect and use the published rules, but you can also manually copy the keep rules if necessary.\n\n\n\n\n\n## Jackson\n\nThe SDK depends on [Jackson](https://github.com/FasterXML/jackson) for JSON serialization/deserialization. It is compatible with version 2.13.4 or higher, but depends on version 2.18.2 by default.\n\nThe SDK throws an exception if it detects an incompatible Jackson version at runtime (e.g. if the default version was overridden in your Maven or Gradle config).\n\nIf the SDK threw an exception, but you\'re _certain_ the version is compatible, then disable the version check using the `checkJacksonVersionCompatibility` on [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt).\n\n> [!CAUTION]\n> We make no guarantee that the SDK works correctly when the Jackson version check is disabled.\n\nAlso note that there are bugs in older Jackson versions that can affect the SDK. We don\'t work around all Jackson bugs ([example](https://github.com/FasterXML/jackson-databind/issues/3240)) and expect users to upgrade Jackson for those instead.\n\n## Network options\n\n### Retries\n\nThe SDK automatically retries 2 times by default, with a short exponential backoff between requests.\n\nOnly the following error types are retried:\n- Connection errors (for example, due to a network connectivity problem)\n- 408 Request Timeout\n- 409 Conflict\n- 429 Rate Limit\n- 5xx Internal\n\nThe API may also explicitly instruct the SDK to retry or not retry a request.\n\nTo set a custom number of retries, configure the client using the `maxRetries` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .maxRetries(4)\n .build();\n```\n\n### Timeouts\n\nRequests time out after 1 minute by default.\n\nTo set a custom timeout, configure the method call using the `timeout` method:\n\n```java\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\n\nIndexListPage page = client.indexes().list(RequestOptions.builder().timeout(Duration.ofSeconds(30)).build());\n```\n\nOr configure the default for all method calls at the client level:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.time.Duration;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .timeout(Duration.ofSeconds(30))\n .build();\n```\n\n### Proxies\n\nTo route requests through a proxy, configure the client using the `proxy` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.net.InetSocketAddress;\nimport java.net.Proxy;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .proxy(new Proxy(\n Proxy.Type.HTTP, new InetSocketAddress(\n "https://example.com", 8080\n )\n ))\n .build();\n```\n\nIf the proxy responds with `407 Proxy Authentication Required`, supply credentials by also configuring `proxyAuthenticator`:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.core.http.ProxyAuthenticator;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .proxy(...)\n // Or a custom implementation of `ProxyAuthenticator`.\n .proxyAuthenticator(ProxyAuthenticator.basic("username", "password"))\n .build();\n```\n\n### Connection pooling\n\nTo customize the underlying OkHttp connection pool, configure the client using the `maxIdleConnections` and `keepAliveDuration` methods:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.time.Duration;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n // If `maxIdleConnections` is set, then `keepAliveDuration` must be set, and vice versa.\n .maxIdleConnections(10)\n .keepAliveDuration(Duration.ofMinutes(2))\n .build();\n```\n\nIf both options are unset, OkHttp\'s default connection pool settings are used.\n\n### HTTPS\n\n> [!NOTE]\n> Most applications should not call these methods, and instead use the system defaults. The defaults include\n> special optimizations that can be lost if the implementations are modified.\n\nTo configure how HTTPS connections are secured, configure the client using the `sslSocketFactory`, `trustManager`, and `hostnameVerifier` methods:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n // If `sslSocketFactory` is set, then `trustManager` must be set, and vice versa.\n .sslSocketFactory(yourSSLSocketFactory)\n .trustManager(yourTrustManager)\n .hostnameVerifier(yourHostnameVerifier)\n .build();\n```\n\n\n\n### Custom HTTP client\n\nThe SDK consists of three artifacts:\n- `llama-cloud-core`\n - Contains core SDK logic\n - Does not depend on [OkHttp](https://square.github.io/okhttp)\n - Exposes [`LlamaCloudClient`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClient.kt), [`LlamaCloudClientAsync`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsync.kt), [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt), and [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), all of which can work with any HTTP client\n- `llama-cloud-client-okhttp`\n - Depends on [OkHttp](https://square.github.io/okhttp)\n - Exposes [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) and [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), which provide a way to construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) and [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), respectively, using OkHttp\n- `llama-cloud`\n - Depends on and exposes the APIs of both `llama-cloud-core` and `llama-cloud-client-okhttp`\n - Does not have its own logic\n\nThis structure allows replacing the SDK\'s default HTTP client without pulling in unnecessary dependencies.\n\n#### Customized [`OkHttpClient`](https://square.github.io/okhttp/3.x/okhttp/okhttp3/OkHttpClient.html)\n\n> [!TIP]\n> Try the available [network options](#network-options) before replacing the default client.\n\nTo use a customized `OkHttpClient`:\n\n1. Replace your [`llama-cloud` dependency](#installation) with `llama-cloud-core`\n2. Copy `llama-cloud-client-okhttp`\'s [`OkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/OkHttpClient.kt) class into your code and customize it\n3. Construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) or [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), similarly to [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), using your customized client\n\n### Completely custom HTTP client\n\nTo use a completely custom HTTP client:\n\n1. Replace your [`llama-cloud` dependency](#installation) with `llama-cloud-core`\n2. Write a class that implements the [`HttpClient`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/http/HttpClient.kt) interface\n3. Construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) or [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), similarly to [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), using your new client class\n\n## Undocumented API functionality\n\nThe SDK is typed for convenient usage of the documented API. However, it also supports working with undocumented or not yet supported parts of the API.\n\n### Parameters\n\nTo set undocumented parameters, call the `putAdditionalHeader`, `putAdditionalQueryParam`, or `putAdditionalBodyProperty` methods on any `Params` class:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .putAdditionalHeader("Secret-Header", "42")\n .putAdditionalQueryParam("secret_query_param", "42")\n .putAdditionalBodyProperty("secretProperty", JsonValue.from("42"))\n .build();\n```\n\nThese can be accessed on the built object later using the `_additionalHeaders()`, `_additionalQueryParams()`, and `_additionalBodyProperties()` methods.\n\nTo set undocumented parameters on _nested_ headers, query params, or body classes, call the `putAdditionalProperty` method on the nested class:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .agenticOptions(ParsingCreateParams.AgenticOptions.builder()\n .putAdditionalProperty("secretProperty", JsonValue.from("42"))\n .build())\n .build();\n```\n\nThese properties can be accessed on the nested built object later using the `_additionalProperties()` method.\n\nTo set a documented parameter or property to an undocumented or not yet supported _value_, pass a [`JsonValue`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt) object to its setter:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(JsonValue.from(42))\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\n```\n\nThe most straightforward way to create a [`JsonValue`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt) is using its `from(...)` method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport java.util.List;\nimport java.util.Map;\n\n// Create primitive JSON values\nJsonValue nullValue = JsonValue.from(null);\nJsonValue booleanValue = JsonValue.from(true);\nJsonValue numberValue = JsonValue.from(42);\nJsonValue stringValue = JsonValue.from("Hello World!");\n\n// Create a JSON array value equivalent to `["Hello", "World"]`\nJsonValue arrayValue = JsonValue.from(List.of(\n "Hello", "World"\n));\n\n// Create a JSON object value equivalent to `{ "a": 1, "b": 2 }`\nJsonValue objectValue = JsonValue.from(Map.of(\n "a", 1,\n "b", 2\n));\n\n// Create an arbitrarily nested JSON equivalent to:\n// {\n// "a": [1, 2],\n// "b": [3, 4]\n// }\nJsonValue complexValue = JsonValue.from(Map.of(\n "a", List.of(\n 1, 2\n ),\n "b", List.of(\n 3, 4\n )\n));\n```\n\nNormally a `Builder` class\'s `build` method will throw [`IllegalStateException`](https://docs.oracle.com/javase/8/docs/api/java/lang/IllegalStateException.html) if any required parameter or property is unset.\n\nTo forcibly omit a required parameter or property, pass [`JsonMissing`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonMissing;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .version(ParsingCreateParams.Version.LATEST)\n .tier(JsonMissing.of())\n .build();\n```\n\n### Response properties\n\nTo access undocumented response properties, call the `_additionalProperties()` method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport java.util.Map;\n\nMap<String, JsonValue> additionalProperties = client.parsing().create(params)._additionalProperties();\nJsonValue secretPropertyValue = additionalProperties.get("secretProperty");\n\nString result = secretPropertyValue.accept(new JsonValue.Visitor<>() {\n @Override\n public String visitNull() {\n return "It\'s null!";\n }\n\n @Override\n public String visitBoolean(boolean value) {\n return "It\'s a boolean!";\n }\n\n @Override\n public String visitNumber(Number value) {\n return "It\'s a number!";\n }\n\n // Other methods include `visitMissing`, `visitString`, `visitArray`, and `visitObject`\n // The default implementation of each unimplemented method delegates to `visitDefault`, which throws by default, but can also be overridden\n});\n```\n\nTo access a property\'s raw JSON value, which may be undocumented, call its `_` prefixed method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonField;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport java.util.Optional;\n\nJsonField<ParsingCreateParams.Tier> tier = client.parsing().create(params)._tier();\n\nif (tier.isMissing()) {\n // The property is absent from the JSON response\n} else if (tier.isNull()) {\n // The property was set to literal null\n} else {\n // Check if value was provided as a string\n // Other methods include `asNumber()`, `asBoolean()`, etc.\n Optional<String> jsonString = tier.asString();\n\n // Try to deserialize into a custom type\n MyClass myObject = tier.asUnknown().orElseThrow().convert(MyClass.class);\n}\n```\n\n### Response validation\n\nIn rare cases, the API may return a response that doesn\'t match the expected type. For example, the SDK may expect a property to contain a `String`, but the API could return something else.\n\nBy default, the SDK will not throw an exception in this case. It will throw [`LlamaCloudInvalidDataException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudInvalidDataException.kt) only if you directly access the property.\n\nValidating the response is _not_ forwards compatible with new types from the API for existing fields.\n\nIf you would still prefer to check that the response is completely well-typed upfront, then either call `validate()`:\n\n```java\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\nParsingCreateResponse parsing = client.parsing().create(params).validate();\n```\n\nOr configure the method call to validate the response using the `responseValidation` method:\n\n```java\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\nParsingCreateResponse parsing = client.parsing().create(\n params, RequestOptions.builder().responseValidation(true).build()\n);\n```\n\nOr configure the default for all method calls at the client level:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .responseValidation(true)\n .build();\n```\n\n## FAQ\n\n### Why don\'t you use plain `enum` classes?\n\nJava `enum` classes are not trivially [forwards compatible](https://www.stainless.com/blog/making-java-enums-forwards-compatible). Using them in the SDK could cause runtime exceptions if the API is updated to respond with a new enum value.\n\n### Why do you represent fields using `JsonField<T>` instead of just plain `T`?\n\nUsing `JsonField<T>` enables a few features:\n\n- Allowing usage of [undocumented API functionality](#undocumented-api-functionality)\n- Lazily [validating the API response against the expected shape](#response-validation)\n- Representing absent vs explicitly null values\n\n### Why don\'t you use [`data` classes](https://kotlinlang.org/docs/data-classes.html)?\n\nIt is not [backwards compatible to add new fields to a data class](https://kotlinlang.org/docs/api-guidelines-backward-compatibility.html#avoid-using-data-classes-in-your-api) and we don\'t want to introduce a breaking change every time we add a field to a class.\n\n### Why don\'t you use checked exceptions?\n\nChecked exceptions are widely considered a mistake in the Java programming language. In fact, they were omitted from Kotlin for this reason.\n\nChecked exceptions:\n\n- Are verbose to handle\n- Encourage error handling at the wrong level of abstraction, where nothing can be done about the error\n- Are tedious to propagate due to the [function coloring problem](https://journal.stuffwithstuff.com/2015/02/01/what-color-is-your-function)\n- Don\'t play well with lambdas (also due to the function coloring problem)\n\n## Semantic versioning\n\nThis package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:\n\n1. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_\n2. Changes that we do not expect to impact the vast majority of users in practice.\n\nWe take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.\n\nWe are keen for your feedback; please open an [issue](https://www.github.com/run-llama/llama-parse-java/issues) with questions, bugs, or suggestions.\n',
|
|
9344
|
+
'# Llama Cloud Java API Library\n\n<!-- x-release-please-start-version -->\n[](https://central.sonatype.com/artifact/ai.llamaindex.llamacloud/llama-cloud/1.10.0)\n[](https://javadoc.io/doc/ai.llamaindex.llamacloud/llama-cloud/1.10.0)\n<!-- x-release-please-end -->\n\nThe Llama Cloud Java SDK provides convenient access to the [Llama Cloud REST API](https://developers.llamaindex.ai/) from applications written in Java.\n\n\n\nIt is generated with [Stainless](https://www.stainless.com/).\n\n## MCP Server\n\nUse the Llama Cloud MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.\n\n[](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBsbGFtYWluZGV4L2xsYW1hLWNsb3VkLW1jcCJdLCJlbnYiOnsiTExBTUFfQ0xPVURfQVBJX0tFWSI6Ik15IEFQSSBLZXkifX0)\n[](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40llamaindex%2Fllama-cloud-mcp%22%5D%2C%22env%22%3A%7B%22LLAMA_CLOUD_API_KEY%22%3A%22My%20API%20Key%22%7D%7D)\n\n> Note: You may need to set environment variables in your MCP client.\n\n<!-- x-release-please-start-version -->\n\nThe REST API documentation can be found on [developers.llamaindex.ai](https://developers.llamaindex.ai/). Javadocs are available on [javadoc.io](https://javadoc.io/doc/ai.llamaindex.llamacloud/llama-cloud/1.10.0).\n\n<!-- x-release-please-end -->\n\n## Installation\n\n<!-- x-release-please-start-version -->\n\n### Gradle\n\n~~~kotlin\nimplementation("ai.llamaindex:llama-cloud:1.10.0")\n~~~\n\n### Maven\n\n~~~xml\n<dependency>\n <groupId>ai.llamaindex</groupId>\n <artifactId>llama-cloud</artifactId>\n <version>1.10.0</version>\n</dependency>\n~~~\n\n<!-- x-release-please-end -->\n\n## Requirements\n\nThis library requires Java 8 or later.\n\n## Usage\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nParsingCreateResponse parsing = client.parsing().create(params);\n```\n\n## Client configuration\n\nConfigure the client using system properties or environment variables:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n```\n\nOr manually:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .apiKey("My API Key")\n .build();\n```\n\nOr using a combination of the two approaches:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n // Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n // Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\n .fromEnv()\n .apiKey("My API Key")\n .build();\n```\n\nSee this table for the available options:\n\n| Setter | System property | Environment variable | Required | Default value |\n| --------- | -------------------- | ---------------------- | -------- | ----------------------------------- |\n| `apiKey` | `llamacloud.apiKey` | `LLAMA_CLOUD_API_KEY` | true | - |\n| `baseUrl` | `llamacloud.baseUrl` | `LLAMA_CLOUD_BASE_URL` | true | `"https://api.cloud.llamaindex.ai"` |\n\nSystem properties take precedence over environment variables.\n\n> [!TIP]\n> Don\'t create more than one client in the same application. Each client has a connection pool and\n> thread pools, which are more efficient to share between requests.\n\n### Modifying configuration\n\nTo temporarily use a modified client configuration, while reusing the same connection and thread pools, call `withOptions()` on any client or service:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\n\nLlamaCloudClient clientWithOptions = client.withOptions(optionsBuilder -> {\n optionsBuilder.baseUrl("https://example.com");\n optionsBuilder.maxRetries(42);\n});\n```\n\nThe `withOptions()` method does not affect the original client or service.\n\n## Requests and responses\n\nTo send a request to the Llama Cloud API, build an instance of some `Params` class and pass it to the corresponding client method. When the response is received, it will be deserialized into an instance of a Java class.\n\nFor example, `client.parsing().create(...)` should be called with an instance of `ParsingCreateParams`, and it will return an instance of `ParsingCreateResponse`.\n\n## Immutability\n\nEach class in the SDK has an associated [builder](https://blogs.oracle.com/javamagazine/post/exploring-joshua-blochs-builder-design-pattern-in-java) or factory method for constructing it.\n\nEach class is [immutable](https://docs.oracle.com/javase/tutorial/essential/concurrency/immutable.html) once constructed. If the class has an associated builder, then it has a `toBuilder()` method, which can be used to convert it back to a builder for making a modified copy.\n\nBecause each class is immutable, builder modification will _never_ affect already built class instances.\n\n## Asynchronous execution\n\nThe default client is synchronous. To switch to asynchronous execution, call the `async()` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\nimport java.util.concurrent.CompletableFuture;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nCompletableFuture<ParsingCreateResponse> parsing = client.async().parsing().create(params);\n```\n\nOr create an asynchronous client from the beginning:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClientAsync;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClientAsync;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\nimport java.util.concurrent.CompletableFuture;\n\n// Configures using the `llamacloud.apiKey` and `llamacloud.baseUrl` system properties\n// Or configures using the `LLAMA_CLOUD_API_KEY` and `LLAMA_CLOUD_BASE_URL` environment variables\nLlamaCloudClientAsync client = LlamaCloudOkHttpClientAsync.fromEnv();\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(ParsingCreateParams.Tier.AGENTIC)\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\nCompletableFuture<ParsingCreateResponse> parsing = client.parsing().create(params);\n```\n\nThe asynchronous client supports the same options as the synchronous one, except most methods return `CompletableFuture`s.\n\n\n\n## File uploads\n\nThe SDK defines methods that accept files.\n\nTo upload a file, pass a [`Path`](https://docs.oracle.com/javase/8/docs/api/java/nio/file/Path.html):\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.nio.file.Paths;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(Paths.get("/path/to/file"))\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nOr an arbitrary [`InputStream`](https://docs.oracle.com/javase/8/docs/api/java/io/InputStream.html):\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.net.URL;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(new URL("https://example.com//path/to/file").openStream())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nOr a `byte[]` array:\n\n```java\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file("content".getBytes())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\nNote that when passing a non-`Path` its filename is unknown so it will not be included in the request. To manually set a filename, pass a [`MultipartField`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.MultipartField;\nimport ai.llamaindex.llamacloud.models.files.FileCreateParams;\nimport ai.llamaindex.llamacloud.models.files.FileCreateResponse;\nimport java.io.InputStream;\nimport java.net.URL;\n\nFileCreateParams params = FileCreateParams.builder()\n .purpose("purpose")\n .file(MultipartField.<InputStream>builder()\n .value(new URL("https://example.com//path/to/file").openStream())\n .filename("/path/to/file")\n .build())\n .build();\nFileCreateResponse file = client.files().create(params);\n```\n\n\n\n## Raw responses\n\nThe SDK defines methods that deserialize responses into instances of Java classes. However, these methods don\'t provide access to the response headers, status code, or the raw response body.\n\nTo access this data, prefix any HTTP method call on a client or service with `withRawResponse()`:\n\n```java\nimport ai.llamaindex.llamacloud.core.http.Headers;\nimport ai.llamaindex.llamacloud.core.http.HttpResponseFor;\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\nimport ai.llamaindex.llamacloud.models.indexes.IndexListParams;\n\nIndexListParams params = IndexListParams.builder()\n .projectId("my-project-id")\n .build();\nHttpResponseFor<IndexListPage> page = client.indexes().withRawResponse().list(params);\n\nint statusCode = page.statusCode();\nHeaders headers = page.headers();\n```\n\nYou can still deserialize the response into an instance of a Java class if needed:\n\n```java\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\n\nIndexListPage parsedPage = page.parse();\n```\n\n## Error handling\n\nThe SDK throws custom unchecked exception types:\n\n- [`LlamaCloudServiceException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudServiceException.kt): Base class for HTTP errors. See this table for which exception subclass is thrown for each HTTP status code:\n\n | Status | Exception |\n | ------ | -------------------------------------------------- |\n | 400 | [`BadRequestException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/BadRequestException.kt) |\n | 401 | [`UnauthorizedException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnauthorizedException.kt) |\n | 403 | [`PermissionDeniedException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/PermissionDeniedException.kt) |\n | 404 | [`NotFoundException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/NotFoundException.kt) |\n | 422 | [`UnprocessableEntityException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnprocessableEntityException.kt) |\n | 429 | [`RateLimitException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/RateLimitException.kt) |\n | 5xx | [`InternalServerException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/InternalServerException.kt) |\n | others | [`UnexpectedStatusCodeException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/UnexpectedStatusCodeException.kt) |\n\n- [`LlamaCloudIoException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudIoException.kt): I/O networking errors.\n\n- [`LlamaCloudRetryableException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudRetryableException.kt): Generic error indicating a failure that could be retried by the client.\n\n- [`LlamaCloudInvalidDataException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudInvalidDataException.kt): Failure to interpret successfully parsed data. For example, when accessing a property that\'s supposed to be required, but the API unexpectedly omitted it from the response.\n\n- [`LlamaCloudException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudException.kt): Base class for all exceptions. Most errors will result in one of the previously mentioned ones, but completely generic errors may be thrown using the base class.\n\n## Pagination\n\nThe SDK defines methods that return a paginated lists of results. It provides convenient ways to access the results either one page at a time or item-by-item across all pages.\n\n### Auto-pagination\n\nTo iterate through all results across all pages, use the `autoPager()` method, which automatically fetches more pages as needed.\n\nWhen using the synchronous client, the method returns an [`Iterable`](https://docs.oracle.com/javase/8/docs/api/java/lang/Iterable.html)\n\n```java\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPage;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\n\nExtractListPage page = client.extract().list();\n\n// Process as an Iterable\nfor (ExtractV2Job extract : page.autoPager()) {\n System.out.println(extract);\n}\n\n// Process as a Stream\npage.autoPager()\n .stream()\n .limit(50)\n .forEach(extract -> System.out.println(extract));\n```\n\nWhen using the asynchronous client, the method returns an [`AsyncStreamResponse`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/http/AsyncStreamResponse.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.http.AsyncStreamResponse;\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPageAsync;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\nimport java.util.Optional;\nimport java.util.concurrent.CompletableFuture;\n\nCompletableFuture<ExtractListPageAsync> pageFuture = client.async().extract().list();\n\npageFuture.thenRun(page -> page.autoPager().subscribe(extract -> {\n System.out.println(extract);\n}));\n\n// If you need to handle errors or completion of the stream\npageFuture.thenRun(page -> page.autoPager().subscribe(new AsyncStreamResponse.Handler<>() {\n @Override\n public void onNext(ExtractV2Job extract) {\n System.out.println(extract);\n }\n\n @Override\n public void onComplete(Optional<Throwable> error) {\n if (error.isPresent()) {\n System.out.println("Something went wrong!");\n throw new RuntimeException(error.get());\n } else {\n System.out.println("No more!");\n }\n }\n}));\n\n// Or use futures\npageFuture.thenRun(page -> page.autoPager()\n .subscribe(extract -> {\n System.out.println(extract);\n })\n .onCompleteFuture()\n .whenComplete((unused, error) -> {\n if (error != null) {\n System.out.println("Something went wrong!");\n throw new RuntimeException(error);\n } else {\n System.out.println("No more!");\n }\n }));\n```\n\n### Manual pagination\n\nTo access individual page items and manually request the next page, use the `items()`,\n`hasNextPage()`, and `nextPage()` methods:\n\n```java\nimport ai.llamaindex.llamacloud.models.extract.ExtractListPage;\nimport ai.llamaindex.llamacloud.models.extract.ExtractV2Job;\n\nExtractListPage page = client.extract().list();\nwhile (true) {\n for (ExtractV2Job extract : page.items()) {\n System.out.println(extract);\n }\n\n if (!page.hasNextPage()) {\n break;\n }\n\n page = page.nextPage();\n}\n```\n\n## Logging\n\nEnable logging by setting the `LLAMA_CLOUD_LOG` environment variable to `info`:\n\n```sh\nexport LLAMA_CLOUD_LOG=info\n```\n\nOr to `debug` for more verbose logging:\n\n```sh\nexport LLAMA_CLOUD_LOG=debug\n```\n\nOr configure the client manually using the `logLevel` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.core.LogLevel;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .logLevel(LogLevel.INFO)\n .build();\n```\n\n## ProGuard and R8\n\nAlthough the SDK uses reflection, it is still usable with [ProGuard](https://github.com/Guardsquare/proguard) and [R8](https://developer.android.com/topic/performance/app-optimization/enable-app-optimization) because `llama-cloud-core` is published with a [configuration file](llama-cloud-core/src/main/resources/META-INF/proguard/llama-cloud-core.pro) containing [keep rules](https://www.guardsquare.com/manual/configuration/usage).\n\nProGuard and R8 should automatically detect and use the published rules, but you can also manually copy the keep rules if necessary.\n\n\n\n\n\n## Jackson\n\nThe SDK depends on [Jackson](https://github.com/FasterXML/jackson) for JSON serialization/deserialization. It is compatible with version 2.13.4 or higher, but depends on version 2.18.2 by default.\n\nThe SDK throws an exception if it detects an incompatible Jackson version at runtime (e.g. if the default version was overridden in your Maven or Gradle config).\n\nIf the SDK threw an exception, but you\'re _certain_ the version is compatible, then disable the version check using the `checkJacksonVersionCompatibility` on [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt).\n\n> [!CAUTION]\n> We make no guarantee that the SDK works correctly when the Jackson version check is disabled.\n\nAlso note that there are bugs in older Jackson versions that can affect the SDK. We don\'t work around all Jackson bugs ([example](https://github.com/FasterXML/jackson-databind/issues/3240)) and expect users to upgrade Jackson for those instead.\n\n## Network options\n\n### Retries\n\nThe SDK automatically retries 2 times by default, with a short exponential backoff between requests.\n\nOnly the following error types are retried:\n- Connection errors (for example, due to a network connectivity problem)\n- 408 Request Timeout\n- 409 Conflict\n- 429 Rate Limit\n- 5xx Internal\n\nThe API may also explicitly instruct the SDK to retry or not retry a request.\n\nTo set a custom number of retries, configure the client using the `maxRetries` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .maxRetries(4)\n .build();\n```\n\n### Timeouts\n\nRequests time out after 1 minute by default.\n\nTo set a custom timeout, configure the method call using the `timeout` method:\n\n```java\nimport ai.llamaindex.llamacloud.models.indexes.IndexListPage;\n\nIndexListPage page = client.indexes().list(RequestOptions.builder().timeout(Duration.ofSeconds(30)).build());\n```\n\nOr configure the default for all method calls at the client level:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.time.Duration;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .timeout(Duration.ofSeconds(30))\n .build();\n```\n\n### Proxies\n\nTo route requests through a proxy, configure the client using the `proxy` method:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.net.InetSocketAddress;\nimport java.net.Proxy;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .proxy(new Proxy(\n Proxy.Type.HTTP, new InetSocketAddress(\n "https://example.com", 8080\n )\n ))\n .build();\n```\n\nIf the proxy responds with `407 Proxy Authentication Required`, supply credentials by also configuring `proxyAuthenticator`:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport ai.llamaindex.llamacloud.core.http.ProxyAuthenticator;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .proxy(...)\n // Or a custom implementation of `ProxyAuthenticator`.\n .proxyAuthenticator(ProxyAuthenticator.basic("username", "password"))\n .build();\n```\n\n### Connection pooling\n\nTo customize the underlying OkHttp connection pool, configure the client using the `maxIdleConnections` and `keepAliveDuration` methods:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\nimport java.time.Duration;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n // If `maxIdleConnections` is set, then `keepAliveDuration` must be set, and vice versa.\n .maxIdleConnections(10)\n .keepAliveDuration(Duration.ofMinutes(2))\n .build();\n```\n\nIf both options are unset, OkHttp\'s default connection pool settings are used.\n\n### HTTPS\n\n> [!NOTE]\n> Most applications should not call these methods, and instead use the system defaults. The defaults include\n> special optimizations that can be lost if the implementations are modified.\n\nTo configure how HTTPS connections are secured, configure the client using the `sslSocketFactory`, `trustManager`, and `hostnameVerifier` methods:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n // If `sslSocketFactory` is set, then `trustManager` must be set, and vice versa.\n .sslSocketFactory(yourSSLSocketFactory)\n .trustManager(yourTrustManager)\n .hostnameVerifier(yourHostnameVerifier)\n .build();\n```\n\n\n\n### Custom HTTP client\n\nThe SDK consists of three artifacts:\n- `llama-cloud-core`\n - Contains core SDK logic\n - Does not depend on [OkHttp](https://square.github.io/okhttp)\n - Exposes [`LlamaCloudClient`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClient.kt), [`LlamaCloudClientAsync`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsync.kt), [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt), and [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), all of which can work with any HTTP client\n- `llama-cloud-client-okhttp`\n - Depends on [OkHttp](https://square.github.io/okhttp)\n - Exposes [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) and [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), which provide a way to construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) and [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), respectively, using OkHttp\n- `llama-cloud`\n - Depends on and exposes the APIs of both `llama-cloud-core` and `llama-cloud-client-okhttp`\n - Does not have its own logic\n\nThis structure allows replacing the SDK\'s default HTTP client without pulling in unnecessary dependencies.\n\n#### Customized [`OkHttpClient`](https://square.github.io/okhttp/3.x/okhttp/okhttp3/OkHttpClient.html)\n\n> [!TIP]\n> Try the available [network options](#network-options) before replacing the default client.\n\nTo use a customized `OkHttpClient`:\n\n1. Replace your [`llama-cloud` dependency](#installation) with `llama-cloud-core`\n2. Copy `llama-cloud-client-okhttp`\'s [`OkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/OkHttpClient.kt) class into your code and customize it\n3. Construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) or [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), similarly to [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), using your customized client\n\n### Completely custom HTTP client\n\nTo use a completely custom HTTP client:\n\n1. Replace your [`llama-cloud` dependency](#installation) with `llama-cloud-core`\n2. Write a class that implements the [`HttpClient`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/http/HttpClient.kt) interface\n3. Construct [`LlamaCloudClientImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientImpl.kt) or [`LlamaCloudClientAsyncImpl`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/client/LlamaCloudClientAsyncImpl.kt), similarly to [`LlamaCloudOkHttpClient`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClient.kt) or [`LlamaCloudOkHttpClientAsync`](llama-cloud-client-okhttp/src/main/kotlin/ai/llamaindex/llamacloud/client/okhttp/LlamaCloudOkHttpClientAsync.kt), using your new client class\n\n## Undocumented API functionality\n\nThe SDK is typed for convenient usage of the documented API. However, it also supports working with undocumented or not yet supported parts of the API.\n\n### Parameters\n\nTo set undocumented parameters, call the `putAdditionalHeader`, `putAdditionalQueryParam`, or `putAdditionalBodyProperty` methods on any `Params` class:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .putAdditionalHeader("Secret-Header", "42")\n .putAdditionalQueryParam("secret_query_param", "42")\n .putAdditionalBodyProperty("secretProperty", JsonValue.from("42"))\n .build();\n```\n\nThese can be accessed on the built object later using the `_additionalHeaders()`, `_additionalQueryParams()`, and `_additionalBodyProperties()` methods.\n\nTo set undocumented parameters on _nested_ headers, query params, or body classes, call the `putAdditionalProperty` method on the nested class:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .agenticOptions(ParsingCreateParams.AgenticOptions.builder()\n .putAdditionalProperty("secretProperty", JsonValue.from("42"))\n .build())\n .build();\n```\n\nThese properties can be accessed on the nested built object later using the `_additionalProperties()` method.\n\nTo set a documented parameter or property to an undocumented or not yet supported _value_, pass a [`JsonValue`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt) object to its setter:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .tier(JsonValue.from(42))\n .version(ParsingCreateParams.Version.LATEST)\n .fileId("abc1234")\n .build();\n```\n\nThe most straightforward way to create a [`JsonValue`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt) is using its `from(...)` method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport java.util.List;\nimport java.util.Map;\n\n// Create primitive JSON values\nJsonValue nullValue = JsonValue.from(null);\nJsonValue booleanValue = JsonValue.from(true);\nJsonValue numberValue = JsonValue.from(42);\nJsonValue stringValue = JsonValue.from("Hello World!");\n\n// Create a JSON array value equivalent to `["Hello", "World"]`\nJsonValue arrayValue = JsonValue.from(List.of(\n "Hello", "World"\n));\n\n// Create a JSON object value equivalent to `{ "a": 1, "b": 2 }`\nJsonValue objectValue = JsonValue.from(Map.of(\n "a", 1,\n "b", 2\n));\n\n// Create an arbitrarily nested JSON equivalent to:\n// {\n// "a": [1, 2],\n// "b": [3, 4]\n// }\nJsonValue complexValue = JsonValue.from(Map.of(\n "a", List.of(\n 1, 2\n ),\n "b", List.of(\n 3, 4\n )\n));\n```\n\nNormally a `Builder` class\'s `build` method will throw [`IllegalStateException`](https://docs.oracle.com/javase/8/docs/api/java/lang/IllegalStateException.html) if any required parameter or property is unset.\n\nTo forcibly omit a required parameter or property, pass [`JsonMissing`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/core/Values.kt):\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonMissing;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\n\nParsingCreateParams params = ParsingCreateParams.builder()\n .version(ParsingCreateParams.Version.LATEST)\n .tier(JsonMissing.of())\n .build();\n```\n\n### Response properties\n\nTo access undocumented response properties, call the `_additionalProperties()` method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonValue;\nimport java.util.Map;\n\nMap<String, JsonValue> additionalProperties = client.parsing().create(params)._additionalProperties();\nJsonValue secretPropertyValue = additionalProperties.get("secretProperty");\n\nString result = secretPropertyValue.accept(new JsonValue.Visitor<>() {\n @Override\n public String visitNull() {\n return "It\'s null!";\n }\n\n @Override\n public String visitBoolean(boolean value) {\n return "It\'s a boolean!";\n }\n\n @Override\n public String visitNumber(Number value) {\n return "It\'s a number!";\n }\n\n // Other methods include `visitMissing`, `visitString`, `visitArray`, and `visitObject`\n // The default implementation of each unimplemented method delegates to `visitDefault`, which throws by default, but can also be overridden\n});\n```\n\nTo access a property\'s raw JSON value, which may be undocumented, call its `_` prefixed method:\n\n```java\nimport ai.llamaindex.llamacloud.core.JsonField;\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateParams;\nimport java.util.Optional;\n\nJsonField<ParsingCreateParams.Tier> tier = client.parsing().create(params)._tier();\n\nif (tier.isMissing()) {\n // The property is absent from the JSON response\n} else if (tier.isNull()) {\n // The property was set to literal null\n} else {\n // Check if value was provided as a string\n // Other methods include `asNumber()`, `asBoolean()`, etc.\n Optional<String> jsonString = tier.asString();\n\n // Try to deserialize into a custom type\n MyClass myObject = tier.asUnknown().orElseThrow().convert(MyClass.class);\n}\n```\n\n### Response validation\n\nIn rare cases, the API may return a response that doesn\'t match the expected type. For example, the SDK may expect a property to contain a `String`, but the API could return something else.\n\nBy default, the SDK will not throw an exception in this case. It will throw [`LlamaCloudInvalidDataException`](llama-cloud-core/src/main/kotlin/ai/llamaindex/llamacloud/errors/LlamaCloudInvalidDataException.kt) only if you directly access the property.\n\nValidating the response is _not_ forwards compatible with new types from the API for existing fields.\n\nIf you would still prefer to check that the response is completely well-typed upfront, then either call `validate()`:\n\n```java\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\nParsingCreateResponse parsing = client.parsing().create(params).validate();\n```\n\nOr configure the method call to validate the response using the `responseValidation` method:\n\n```java\nimport ai.llamaindex.llamacloud.models.parsing.ParsingCreateResponse;\n\nParsingCreateResponse parsing = client.parsing().create(\n params, RequestOptions.builder().responseValidation(true).build()\n);\n```\n\nOr configure the default for all method calls at the client level:\n\n```java\nimport ai.llamaindex.llamacloud.client.LlamaCloudClient;\nimport ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient;\n\nLlamaCloudClient client = LlamaCloudOkHttpClient.builder()\n .fromEnv()\n .responseValidation(true)\n .build();\n```\n\n## FAQ\n\n### Why don\'t you use plain `enum` classes?\n\nJava `enum` classes are not trivially [forwards compatible](https://www.stainless.com/blog/making-java-enums-forwards-compatible). Using them in the SDK could cause runtime exceptions if the API is updated to respond with a new enum value.\n\n### Why do you represent fields using `JsonField<T>` instead of just plain `T`?\n\nUsing `JsonField<T>` enables a few features:\n\n- Allowing usage of [undocumented API functionality](#undocumented-api-functionality)\n- Lazily [validating the API response against the expected shape](#response-validation)\n- Representing absent vs explicitly null values\n\n### Why don\'t you use [`data` classes](https://kotlinlang.org/docs/data-classes.html)?\n\nIt is not [backwards compatible to add new fields to a data class](https://kotlinlang.org/docs/api-guidelines-backward-compatibility.html#avoid-using-data-classes-in-your-api) and we don\'t want to introduce a breaking change every time we add a field to a class.\n\n### Why don\'t you use checked exceptions?\n\nChecked exceptions are widely considered a mistake in the Java programming language. In fact, they were omitted from Kotlin for this reason.\n\nChecked exceptions:\n\n- Are verbose to handle\n- Encourage error handling at the wrong level of abstraction, where nothing can be done about the error\n- Are tedious to propagate due to the [function coloring problem](https://journal.stuffwithstuff.com/2015/02/01/what-color-is-your-function)\n- Don\'t play well with lambdas (also due to the function coloring problem)\n\n## Semantic versioning\n\nThis package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:\n\n1. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_\n2. Changes that we do not expect to impact the vast majority of users in practice.\n\nWe take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.\n\nWe are keen for your feedback; please open an [issue](https://www.github.com/run-llama/llama-parse-java/issues) with questions, bugs, or suggestions.\n',
|
|
8959
9345
|
},
|
|
8960
9346
|
{
|
|
8961
9347
|
language: 'csharp',
|