@llamaindex/llama-cloud-mcp 2.8.0 → 2.9.0
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/local-docs-search.d.mts.map +1 -1
- package/local-docs-search.d.ts.map +1 -1
- package/local-docs-search.js +44 -38
- package/local-docs-search.js.map +1 -1
- package/local-docs-search.mjs +44 -38
- package/local-docs-search.mjs.map +1 -1
- package/package.json +2 -2
- package/server.js +1 -1
- package/server.mjs +1 -1
- package/src/local-docs-search.ts +44 -38
- package/src/server.ts +1 -1
package/local-docs-search.mjs
CHANGED
|
@@ -206,7 +206,7 @@ const EMBEDDED_METHODS = [
|
|
|
206
206
|
qualified: 'client.parsing.create',
|
|
207
207
|
params: [
|
|
208
208
|
"tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus';",
|
|
209
|
-
"version: 'latest' | '2026-05
|
|
209
|
+
"version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | string;",
|
|
210
210
|
'organization_id?: string;',
|
|
211
211
|
'project_id?: string;',
|
|
212
212
|
'agentic_options?: { custom_prompt?: string; };',
|
|
@@ -217,15 +217,15 @@ const EMBEDDED_METHODS = [
|
|
|
217
217
|
'file_id?: string;',
|
|
218
218
|
'http_proxy?: string;',
|
|
219
219
|
'input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; pdf?: object; presentation?: { 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; }; };',
|
|
220
|
-
"output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: 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; }; };",
|
|
220
|
+
"output_options?: { additional_outputs?: string[]; extract_printed_page_number?: boolean; granular_bboxes?: 'cell' | 'line' | 'word'[]; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: 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; }; };",
|
|
221
221
|
'page_ranges?: { max_pages?: number; target_pages?: string; };',
|
|
222
222
|
'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; }; };',
|
|
223
|
-
"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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-05
|
|
223
|
+
"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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; };",
|
|
224
224
|
'source_url?: string;',
|
|
225
|
-
|
|
225
|
+
"webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: string; }[];",
|
|
226
226
|
],
|
|
227
227
|
response: "{ id: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; }",
|
|
228
|
-
markdown: "## create\n\n`client.parsing.create(tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus', version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | string, organization_id?: string, project_id?: 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, file_id?: string, http_proxy?: string, input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; pdf?: object; presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }, 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }, source_url?: string, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: string; }[]): { id: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; }`\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'`\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' | '2026-05-21' | '2026-04-09' | '2025-12-11' | string`\n Tier version. Use 'latest' for the current stable version, or pin a dated version for reproducible results. See GET /api/v2/parse/versions for the per-tier list.\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- `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; }; pdf?: object; presentation?: { 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 - `pdf?: object`\n PDF-specific parsing options (applies to .pdf files)\n - `presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: 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; }; }`\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 - `images_to_save?: 'screenshot' | 'embedded' | 'layout'[]`\n Image categories to extract and save. Options: 'screenshot' (full page renders useful for visual QA), 'embedded' (images found within the document), 'layout' (cropped regions from layout detection like figures and diagrams). Empty list saves no images\n - `markdown?: { annotate_links?: 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 - `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\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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | '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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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 - `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 - `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_plus' | 'agentic' | '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- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; 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: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; }`\n A parse job.\n\n - `id: string`\n - `project_id: string`\n - `status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n - `created_at?: string`\n - `error_message?: string`\n - `name?: string`\n - `tier?: string`\n - `updated_at?: string`\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```",
|
|
228
|
+
markdown: "## create\n\n`client.parsing.create(tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus', version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | string, organization_id?: string, project_id?: 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, file_id?: string, http_proxy?: string, input_options?: { html?: { make_all_elements_visible?: boolean; remove_fixed_elements?: boolean; remove_navigation_elements?: boolean; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }, 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }, source_url?: string, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: string; }[]): { id: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; }`\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'`\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' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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`: `2025-12-11`\n- `cost_effective`: `2026-06-05`\n- `agentic`: `2026-06-04`\n- `agentic_plus`: `2026-06-04`\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- `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; }; pdf?: object; presentation?: { 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 - `pdf?: object`\n PDF-specific parsing options (applies to .pdf files)\n - `presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: { compact_markdown_tables?: boolean; markdown_table_multiline_separator?: string; merge_continued_tables?: boolean; output_tables_as_markdown?: 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; }; }`\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?: 'screenshot' | 'embedded' | 'layout'[]`\n Image categories to extract and save. Options: 'screenshot' (full page renders useful for visual QA), 'embedded' (images found within the document), 'layout' (cropped regions from layout detection like figures and diagrams). Empty list saves no images\n - `markdown?: { annotate_links?: 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 - `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\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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: string[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | '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_plus' | 'agentic' | 'efficient'; tier?: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version?: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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 - `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 - `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_plus' | 'agentic' | '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- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; 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: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; error_message?: string; name?: string; tier?: string; updated_at?: string; }`\n A parse job.\n\n - `id: string`\n - `project_id: string`\n - `status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n - `created_at?: string`\n - `error_message?: string`\n - `name?: string`\n - `tier?: string`\n - `updated_at?: string`\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```",
|
|
229
229
|
perLanguage: {
|
|
230
230
|
typescript: {
|
|
231
231
|
method: 'client.parsing.create',
|
|
@@ -341,12 +341,12 @@ const EMBEDDED_METHODS = [
|
|
|
341
341
|
'file_input: string;',
|
|
342
342
|
'organization_id?: string;',
|
|
343
343
|
'project_id?: string;',
|
|
344
|
-
"configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean;
|
|
344
|
+
"configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; };",
|
|
345
345
|
'configuration_id?: string;',
|
|
346
346
|
'webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[];',
|
|
347
347
|
],
|
|
348
|
-
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean;
|
|
349
|
-
markdown: "## create\n\n`client.extract.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean;
|
|
348
|
+
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }",
|
|
349
|
+
markdown: "## create\n\n`client.extract.create(file_input: string, organization_id?: string, project_id?: string, configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; }, configuration_id?: string, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 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; }`\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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 - `cite_sources?: boolean`\n Include citations in results\n - `confidence_scores?: boolean`\n Include confidence scores in results\n - `extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'`\n 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\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\n - `parse_tier?: string`\n Parse tier to use before extraction. Defaults to the extract tier if not specified.\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?: 'cost_effective' | 'agentic'`\n Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page)\n - `version?: string`\n Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }`\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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_extracted?: 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```",
|
|
350
350
|
perLanguage: {
|
|
351
351
|
typescript: {
|
|
352
352
|
method: 'client.extract.create',
|
|
@@ -392,8 +392,8 @@ const EMBEDDED_METHODS = [
|
|
|
392
392
|
'project_id?: string;',
|
|
393
393
|
"status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED';",
|
|
394
394
|
],
|
|
395
|
-
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean;
|
|
396
|
-
markdown: "## 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?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'): { 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; }`\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?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\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; cite_sources?: boolean; confidence_scores?: boolean;
|
|
395
|
+
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }",
|
|
396
|
+
markdown: "## 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?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'): { 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; }`\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?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }`\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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_extracted?: 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```",
|
|
397
397
|
perLanguage: {
|
|
398
398
|
typescript: {
|
|
399
399
|
method: 'client.extract.list',
|
|
@@ -425,8 +425,8 @@ const EMBEDDED_METHODS = [
|
|
|
425
425
|
stainlessPath: '(resource) extract > (method) get',
|
|
426
426
|
qualified: 'client.extract.get',
|
|
427
427
|
params: ['job_id: string;', 'expand?: string[];', 'organization_id?: string;', 'project_id?: string;'],
|
|
428
|
-
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean;
|
|
429
|
-
markdown: "## 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; }`\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,\nand `expand=extract_metadata` for per-field metadata.\n\n### Parameters\n\n- `job_id: string`\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata\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; cite_sources?: boolean; confidence_scores?: boolean;
|
|
428
|
+
response: "{ id: string; created_at: string; file_input: string; project_id: string; status: string; updated_at: string; configuration?: { data_schema: object; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }",
|
|
429
|
+
markdown: "## 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; }`\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,\nand `expand=extract_metadata` for per-field metadata.\n\n### Parameters\n\n- `job_id: string`\n\n- `expand?: string[]`\n Additional fields to include: configuration, extract_metadata\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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; }; }`\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; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; 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_extracted?: 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```",
|
|
430
430
|
perLanguage: {
|
|
431
431
|
typescript: {
|
|
432
432
|
method: 'client.extract.get',
|
|
@@ -532,7 +532,7 @@ const EMBEDDED_METHODS = [
|
|
|
532
532
|
'prompt?: string;',
|
|
533
533
|
],
|
|
534
534
|
response: "{ 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'; use_experimental_processing?: boolean; } | object; }",
|
|
535
|
-
markdown: "## 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: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean;
|
|
535
|
+
markdown: "## 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: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; }`\n Request body for creating a product configuration.\n\n - `name: string`\n - `parameters: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; 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```",
|
|
536
536
|
perLanguage: {
|
|
537
537
|
typescript: {
|
|
538
538
|
method: 'client.extract.generateSchema',
|
|
@@ -570,10 +570,10 @@ const EMBEDDED_METHODS = [
|
|
|
570
570
|
'project_id?: string;',
|
|
571
571
|
"mode?: 'FAST' | 'MULTIMODAL';",
|
|
572
572
|
'parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: number[]; };',
|
|
573
|
-
|
|
573
|
+
"webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: string; }[];",
|
|
574
574
|
],
|
|
575
575
|
response: "{ id: string; project_id: string; rules: { description: string; type: string; }[]; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; user_id: string; created_at?: string; effective_at?: string; error_message?: string; job_record_id?: string; mode?: 'FAST' | 'MULTIMODAL'; parsing_configuration?: { lang?: parsing_languages; max_pages?: number; target_pages?: number[]; }; updated_at?: string; }",
|
|
576
|
-
markdown: "## create\n\n`client.classifier.jobs.create(file_ids: string[], rules: { description: string; type: string; }[], organization_id?: string, project_id?: string, mode?: 'FAST' | 'MULTIMODAL', parsing_configuration?: { lang?: parsing_languages; max_pages?: number; target_pages?: number[]; }, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: string; }[]): { id: string; project_id: string; rules: classifier_rule[]; status: status_enum; user_id: string; created_at?: string; effective_at?: string; error_message?: string; job_record_id?: string; mode?: 'FAST' | 'MULTIMODAL'; parsing_configuration?: classify_parsing_configuration; updated_at?: string; }`\n\n**post** `/api/v1/classifier/jobs`\n\nCreate a classify job. Experimental: not production-ready and subject to change.\n\n### Parameters\n\n- `file_ids: string[]`\n The IDs of the files to classify\n\n- `rules: { description: string; type: string; }[]`\n The rules to classify the files\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `mode?: 'FAST' | 'MULTIMODAL'`\n The classification mode to use\n\n- `parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: number[]; }`\n The configuration for the parsing job\n - `lang?: string`\n The language to parse the files in\n - `max_pages?: number`\n The maximum number of pages to parse\n - `target_pages?: number[]`\n The pages to target for parsing (0-indexed, so first page is at 0)\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: string; }[]`\n List of webhook configurations for notifications\n\n### Returns\n\n- `{ id: string; project_id: string; rules: { description: string; type: string; }[]; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; user_id: string; created_at?: string; effective_at?: string; error_message?: string; job_record_id?: string; mode?: 'FAST' | 'MULTIMODAL'; parsing_configuration?: { lang?: parsing_languages; max_pages?: number; target_pages?: number[]; }; updated_at?: string; }`\n A classify job.\n\n - `id: string`\n - `project_id: string`\n - `rules: { description: string; type: string; }[]`\n - `status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n - `user_id: string`\n - `created_at?: string`\n - `effective_at?: string`\n - `error_message?: string`\n - `job_record_id?: string`\n - `mode?: 'FAST' | 'MULTIMODAL'`\n - `parsing_configuration?: { lang?: string; max_pages?: number; target_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 classifyJob = await client.classifier.jobs.create({ file_ids: ['182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'], rules: [{ description: 'contains invoice number, line items, and total amount', type: 'invoice' }] });\n\nconsole.log(classifyJob);\n```",
|
|
576
|
+
markdown: "## create\n\n`client.classifier.jobs.create(file_ids: string[], rules: { description: string; type: string; }[], organization_id?: string, project_id?: string, mode?: 'FAST' | 'MULTIMODAL', parsing_configuration?: { lang?: parsing_languages; max_pages?: number; target_pages?: number[]; }, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: string; }[]): { id: string; project_id: string; rules: classifier_rule[]; status: status_enum; user_id: string; created_at?: string; effective_at?: string; error_message?: string; job_record_id?: string; mode?: 'FAST' | 'MULTIMODAL'; parsing_configuration?: classify_parsing_configuration; updated_at?: string; }`\n\n**post** `/api/v1/classifier/jobs`\n\nCreate a classify job. Experimental: not production-ready and subject to change.\n\n### Parameters\n\n- `file_ids: string[]`\n The IDs of the files to classify\n\n- `rules: { description: string; type: string; }[]`\n The rules to classify the files\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `mode?: 'FAST' | 'MULTIMODAL'`\n The classification mode to use\n\n- `parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: number[]; }`\n The configuration for the parsing job\n - `lang?: string`\n The language to parse the files in\n - `max_pages?: number`\n The maximum number of pages to parse\n - `target_pages?: number[]`\n The pages to target for parsing (0-indexed, so first page is at 0)\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: string; }[]`\n List of webhook configurations for notifications\n\n### Returns\n\n- `{ id: string; project_id: string; rules: { description: string; type: string; }[]; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; user_id: string; created_at?: string; effective_at?: string; error_message?: string; job_record_id?: string; mode?: 'FAST' | 'MULTIMODAL'; parsing_configuration?: { lang?: parsing_languages; max_pages?: number; target_pages?: number[]; }; updated_at?: string; }`\n A classify job.\n\n - `id: string`\n - `project_id: string`\n - `rules: { description: string; type: string; }[]`\n - `status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n - `user_id: string`\n - `created_at?: string`\n - `effective_at?: string`\n - `error_message?: string`\n - `job_record_id?: string`\n - `mode?: 'FAST' | 'MULTIMODAL'`\n - `parsing_configuration?: { lang?: string; max_pages?: number; target_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 classifyJob = await client.classifier.jobs.create({ file_ids: ['182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'], rules: [{ description: 'contains invoice number, line items, and total amount', type: 'invoice' }] });\n\nconsole.log(classifyJob);\n```",
|
|
577
577
|
perLanguage: {
|
|
578
578
|
typescript: {
|
|
579
579
|
method: 'client.classifier.jobs.create',
|
|
@@ -715,26 +715,26 @@ const EMBEDDED_METHODS = [
|
|
|
715
715
|
'project_id?: string;',
|
|
716
716
|
],
|
|
717
717
|
response: "{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }",
|
|
718
|
-
markdown: "## create\n\n`client.batches.create(config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }, source_directory_id: string, organization_id?: string, project_id?: string): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**post** `/api/v2/batches`\n\nCreate a batch over a source directory and start processing asynchronously.\n\n### Parameters\n\n- `config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }`\n Batch configuration snapshot to apply to this source directory.\n - `job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }`\n Job to create for each file in the source directory.\n\n- `source_directory_id: string`\n Directory whose files should be processed.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-
|
|
718
|
+
markdown: "## create\n\n`client.batches.create(config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }, source_directory_id: string, organization_id?: string, project_id?: string): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**post** `/api/v2/batches`\n\nCreate a batch over a source directory and start processing asynchronously.\n\n### Parameters\n\n- `config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }`\n Batch configuration snapshot to apply to this source directory.\n - `job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }`\n Job to create for each file in the source directory.\n\n- `source_directory_id: string`\n Directory whose files should be processed.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-PARSE_AGENTIC\"\n }\n },\n \"status\": \"COMPLETED\",\n \"results\": [\n {\n \"source_directory_file_id\": \"dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"job_reference\": {\n \"type\": \"parse_v2\",\n \"id\": \"pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\"\n },\n \"error_message\": null\n }\n ]\n }\n\nBatch-level ``FAILED`` means the orchestration failed and cannot provide a\nreliable per-file result set. ``results`` is only populated when explicitly\nrequested with ``expand=results`` and may be ``null`` while a batch is still\nrunning.\n\n - `id: string`\n - `config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }`\n - `project_id: string`\n - `source_directory_id: string`\n - `status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n - `created_at?: string`\n - `results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst batch = await client.batches.create({\n config: { job: { configuration_id: 'cfg-PARSE_AGENTIC', type: 'parse_v2' } },\n source_directory_id: 'dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',\n});\n\nconsole.log(batch);\n```",
|
|
719
719
|
perLanguage: {
|
|
720
720
|
typescript: {
|
|
721
721
|
method: 'client.batches.create',
|
|
722
|
-
example: "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 batch = await client.batches.create({\n config: {
|
|
722
|
+
example: "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 batch = await client.batches.create({\n config: { job: { configuration_id: 'cfg-PARSE_AGENTIC', type: 'parse_v2' } },\n source_directory_id: 'dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',\n});\n\nconsole.log(batch.id);",
|
|
723
723
|
},
|
|
724
724
|
python: {
|
|
725
725
|
method: 'batches.create',
|
|
726
|
-
example: '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)\nbatch = client.batches.create(\n config={\n "job": {\n "configuration_id": "cfg-
|
|
726
|
+
example: '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)\nbatch = client.batches.create(\n config={\n "job": {\n "configuration_id": "cfg-PARSE_AGENTIC",\n "type": "parse_v2",\n }\n },\n source_directory_id="dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",\n)\nprint(batch.id)',
|
|
727
727
|
},
|
|
728
728
|
go: {
|
|
729
729
|
method: 'client.Batches.New',
|
|
730
|
-
example: 'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/stainless-sdks/llamacloud-prod-go"\n\t"github.com/stainless-sdks/llamacloud-prod-go/option"\n)\n\nfunc main() {\n\tclient := llamacloudprod.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\tbatch, err := client.Batches.New(context.TODO(), llamacloudprod.BatchNewParams{\n\t\tConfig: llamacloudprod.BatchNewParamsConfig{\n\t\t\tJob: llamacloudprod.BatchNewParamsConfigJob{\n\t\t\t\tConfigurationID: "cfg-
|
|
730
|
+
example: 'package main\n\nimport (\n\t"context"\n\t"fmt"\n\n\t"github.com/stainless-sdks/llamacloud-prod-go"\n\t"github.com/stainless-sdks/llamacloud-prod-go/option"\n)\n\nfunc main() {\n\tclient := llamacloudprod.NewClient(\n\t\toption.WithAPIKey("My API Key"),\n\t)\n\tbatch, err := client.Batches.New(context.TODO(), llamacloudprod.BatchNewParams{\n\t\tConfig: llamacloudprod.BatchNewParamsConfig{\n\t\t\tJob: llamacloudprod.BatchNewParamsConfigJob{\n\t\t\t\tConfigurationID: "cfg-PARSE_AGENTIC",\n\t\t\t\tType: llamacloudprod.BatchNewParamsConfigJobTypeParseV2,\n\t\t\t},\n\t\t},\n\t\tSourceDirectoryID: "dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf("%+v\\n", batch.ID)\n}\n',
|
|
731
731
|
},
|
|
732
732
|
cli: {
|
|
733
733
|
method: 'batches create',
|
|
734
|
-
example: "llamacloud-prod batches create \\\n --api-key 'My API Key' \\\n --config '{job: {configuration_id: cfg-
|
|
734
|
+
example: "llamacloud-prod batches create \\\n --api-key 'My API Key' \\\n --config '{job: {configuration_id: cfg-PARSE_AGENTIC, type: parse_v2}}' \\\n --source-directory-id dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
|
|
735
735
|
},
|
|
736
736
|
http: {
|
|
737
|
-
example: 'curl https://api.cloud.llamaindex.ai/api/v2/batches \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "config": {\n "job": {\n "configuration_id": "cfg-
|
|
737
|
+
example: 'curl https://api.cloud.llamaindex.ai/api/v2/batches \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "config": {\n "job": {\n "configuration_id": "cfg-PARSE_AGENTIC",\n "type": "parse_v2"\n }\n },\n "source_directory_id": "dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"\n }\'',
|
|
738
738
|
},
|
|
739
739
|
},
|
|
740
740
|
},
|
|
@@ -757,7 +757,7 @@ const EMBEDDED_METHODS = [
|
|
|
757
757
|
"status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED';",
|
|
758
758
|
],
|
|
759
759
|
response: "{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }",
|
|
760
|
-
markdown: "## list\n\n`client.batches.list(created_at_on_or_after?: string, created_at_on_or_before?: string, organization_id?: string, page_size?: number, page_token?: string, project_id?: string, source_directory_id?: string, status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**get** `/api/v2/batches`\n\nList batches for the current project.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n\n- `created_at_on_or_before?: string`\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `source_directory_id?: string`\n\n- `status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-
|
|
760
|
+
markdown: "## list\n\n`client.batches.list(created_at_on_or_after?: string, created_at_on_or_before?: string, organization_id?: string, page_size?: number, page_token?: string, project_id?: string, source_directory_id?: string, status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**get** `/api/v2/batches`\n\nList batches for the current project.\n\n### Parameters\n\n- `created_at_on_or_after?: string`\n\n- `created_at_on_or_before?: string`\n\n- `organization_id?: string`\n\n- `page_size?: number`\n\n- `page_token?: string`\n\n- `project_id?: string`\n\n- `source_directory_id?: string`\n\n- `status?: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-PARSE_AGENTIC\"\n }\n },\n \"status\": \"COMPLETED\",\n \"results\": [\n {\n \"source_directory_file_id\": \"dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"job_reference\": {\n \"type\": \"parse_v2\",\n \"id\": \"pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\"\n },\n \"error_message\": null\n }\n ]\n }\n\nBatch-level ``FAILED`` means the orchestration failed and cannot provide a\nreliable per-file result set. ``results`` is only populated when explicitly\nrequested with ``expand=results`` and may be ``null`` while a batch is still\nrunning.\n\n - `id: string`\n - `config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }`\n - `project_id: string`\n - `source_directory_id: string`\n - `status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n - `created_at?: string`\n - `results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]`\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 batchListResponse of client.batches.list()) {\n console.log(batchListResponse);\n}\n```",
|
|
761
761
|
perLanguage: {
|
|
762
762
|
typescript: {
|
|
763
763
|
method: 'client.batches.list',
|
|
@@ -790,7 +790,7 @@ const EMBEDDED_METHODS = [
|
|
|
790
790
|
qualified: 'client.batches.get',
|
|
791
791
|
params: ['batch_id: string;', 'expand?: string[];', 'organization_id?: string;', 'project_id?: string;'],
|
|
792
792
|
response: "{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }",
|
|
793
|
-
markdown: "## get\n\n`client.batches.get(batch_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**get** `/api/v2/batches/{batch_id}`\n\nGet a batch by ID.\n\n### Parameters\n\n- `batch_id: string`\n\n- `expand?: string[]`\n Fields to expand. Supported value: results.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-
|
|
793
|
+
markdown: "## get\n\n`client.batches.get(batch_id: string, expand?: string[], organization_id?: string, project_id?: string): { id: string; config: object; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: object[]; updated_at?: string; }`\n\n**get** `/api/v2/batches/{batch_id}`\n\nGet a batch by ID.\n\n### Parameters\n\n- `batch_id: string`\n\n- `expand?: string[]`\n Fields to expand. Supported value: results.\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }; project_id: string; source_directory_id: string; status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'; created_at?: string; results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]; updated_at?: string; }`\n A top-level batch.\n\nExample:\n {\n \"id\": \"bat-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"project_id\": \"prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"source_directory_id\": \"dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"config\": {\n \"job\": {\n \"type\": \"parse_v2\",\n \"configuration_id\": \"cfg-PARSE_AGENTIC\"\n }\n },\n \"status\": \"COMPLETED\",\n \"results\": [\n {\n \"source_directory_file_id\": \"dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\",\n \"job_reference\": {\n \"type\": \"parse_v2\",\n \"id\": \"pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee\"\n },\n \"error_message\": null\n }\n ]\n }\n\nBatch-level ``FAILED`` means the orchestration failed and cannot provide a\nreliable per-file result set. ``results`` is only populated when explicitly\nrequested with ``expand=results`` and may be ``null`` while a batch is still\nrunning.\n\n - `id: string`\n - `config: { job: { configuration_id: string; type: 'parse_v2' | 'extract_v2'; }; }`\n - `project_id: string`\n - `source_directory_id: string`\n - `status: 'PENDING' | 'THROTTLED' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED'`\n - `created_at?: string`\n - `results?: { source_directory_file_id: string; error_message?: string; job_reference?: { id: string; type: 'parse_v2' | 'extract_v2'; }; }[]`\n - `updated_at?: string`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst batch = await client.batches.get('batch_id');\n\nconsole.log(batch);\n```",
|
|
794
794
|
perLanguage: {
|
|
795
795
|
typescript: {
|
|
796
796
|
method: 'client.batches.get',
|
|
@@ -830,9 +830,10 @@ const EMBEDDED_METHODS = [
|
|
|
830
830
|
'file_input?: string;',
|
|
831
831
|
'parse_job_id?: string;',
|
|
832
832
|
'transaction_id?: string;',
|
|
833
|
+
'webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[];',
|
|
833
834
|
],
|
|
834
835
|
response: "{ id: string; configuration: { rules: object[]; mode?: 'FAST'; parsing_configuration?: object; }; document_input_type: 'url' | 'file_id' | 'parse_job_id'; file_input: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_job_id?: string; result?: { confidence: number; reasoning: string; type: string; }; transaction_id?: string; updated_at?: string; }",
|
|
835
|
-
markdown: "## create\n\n`client.classify.create(organization_id?: string, project_id?: string, configuration?: { rules: object[]; mode?: 'FAST'; parsing_configuration?: object; }, configuration_id?: string, file_id?: string, file_input?: string, parse_job_id?: string, transaction_id?: string): { id: string; configuration: classify_configuration; document_input_type: 'url' | 'file_id' | 'parse_job_id'; file_input: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_job_id?: string; result?: classify_result; transaction_id?: string; updated_at?: string; }`\n\n**post** `/api/v2/classify`\n\nCreate a classify job.\n\nClassifies a document against a set of rules. Set `file_input`\nto a file ID (`dfl-...`) or parse job ID (`pjb-...`), and provide\neither inline `configuration` with rules or a `configuration_id`\nreferencing a saved preset.\n\nEach rule has a `type` (the label to assign) and a `description`\n(natural language criteria). The classifier returns the best\nmatching rule with a confidence score.\n\nThe job runs asynchronously. Poll `GET /classify/{job_id}` to\ncheck status and retrieve results.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; }`\n Configuration for a classify job.\n - `rules: { description: string; type: string; }[]`\n Classify rules to evaluate against the document (at least one required)\n - `mode?: 'FAST'`\n Classify execution mode\n - `parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }`\n Parsing configuration for classify jobs.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `file_id?: string`\n Deprecated: use file_input instead\n\n- `file_input?: string`\n File ID or parse job ID to classify\n\n- `parse_job_id?: string`\n Deprecated: use file_input instead\n\n- `transaction_id?: string`\n Idempotency key scoped to the project\n\n### Returns\n\n- `{ id: string; configuration: { rules: object[]; mode?: 'FAST'; parsing_configuration?: object; }; document_input_type: 'url' | 'file_id' | 'parse_job_id'; file_input: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_job_id?: string; result?: { confidence: number; reasoning: string; type: string; }; transaction_id?: string; updated_at?: string; }`\n Response for a classify job.\n\n - `id: string`\n - `configuration: { rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; }`\n - `document_input_type: 'url' | 'file_id' | 'parse_job_id'`\n - `file_input: string`\n - `project_id: string`\n - `status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_job_id?: string`\n - `result?: { confidence: number; reasoning: string; type: 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 classify = await client.classify.create();\n\nconsole.log(classify);\n```",
|
|
836
|
+
markdown: "## create\n\n`client.classify.create(organization_id?: string, project_id?: string, configuration?: { rules: object[]; mode?: 'FAST'; parsing_configuration?: object; }, configuration_id?: string, file_id?: string, file_input?: string, parse_job_id?: string, transaction_id?: string, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]): { id: string; configuration: classify_configuration; document_input_type: 'url' | 'file_id' | 'parse_job_id'; file_input: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_job_id?: string; result?: classify_result; transaction_id?: string; updated_at?: string; }`\n\n**post** `/api/v2/classify`\n\nCreate a classify job.\n\nClassifies a document against a set of rules. Set `file_input`\nto a file ID (`dfl-...`) or parse job ID (`pjb-...`), and provide\neither inline `configuration` with rules or a `configuration_id`\nreferencing a saved preset.\n\nEach rule has a `type` (the label to assign) and a `description`\n(natural language criteria). The classifier returns the best\nmatching rule with a confidence score.\n\nThe job runs asynchronously. Poll `GET /classify/{job_id}` to\ncheck status and retrieve results.\n\n### Parameters\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `configuration?: { rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; }`\n Configuration for a classify job.\n - `rules: { description: string; type: string; }[]`\n Classify rules to evaluate against the document (at least one required)\n - `mode?: 'FAST'`\n Classify execution mode\n - `parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }`\n Parsing configuration for classify jobs.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `file_id?: string`\n Deprecated: use file_input instead\n\n- `file_input?: string`\n File ID or parse job ID to classify\n\n- `parse_job_id?: string`\n Deprecated: use file_input instead\n\n- `transaction_id?: string`\n Idempotency key scoped to the project\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n\n### Returns\n\n- `{ id: string; configuration: { rules: object[]; mode?: 'FAST'; parsing_configuration?: object; }; document_input_type: 'url' | 'file_id' | 'parse_job_id'; file_input: string; project_id: string; status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'; user_id: string; configuration_id?: string; created_at?: string; error_message?: string; parse_job_id?: string; result?: { confidence: number; reasoning: string; type: string; }; transaction_id?: string; updated_at?: string; }`\n Response for a classify job.\n\n - `id: string`\n - `configuration: { rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; }`\n - `document_input_type: 'url' | 'file_id' | 'parse_job_id'`\n - `file_input: string`\n - `project_id: string`\n - `status: 'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED'`\n - `user_id: string`\n - `configuration_id?: string`\n - `created_at?: string`\n - `error_message?: string`\n - `parse_job_id?: string`\n - `result?: { confidence: number; reasoning: string; type: 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 classify = await client.classify.create();\n\nconsole.log(classify);\n```",
|
|
836
837
|
perLanguage: {
|
|
837
838
|
typescript: {
|
|
838
839
|
method: 'client.classify.create',
|
|
@@ -941,12 +942,12 @@ const EMBEDDED_METHODS = [
|
|
|
941
942
|
qualified: 'client.configurations.create',
|
|
942
943
|
params: [
|
|
943
944
|
'name: string;',
|
|
944
|
-
"parameters: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean;
|
|
945
|
+
"parameters: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; };",
|
|
945
946
|
'organization_id?: string;',
|
|
946
947
|
'project_id?: string;',
|
|
947
948
|
],
|
|
948
949
|
response: "{ 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'; use_experimental_processing?: boolean; } | object; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
949
|
-
markdown: "## create\n\n`client.configurations.create(name: string, parameters: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }, organization_id?: string, project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: 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'; 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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: [{ name: 'x' }], product_type: 'split_v1' },\n});\n\nconsole.log(configurationResponse);\n```",
|
|
950
|
+
markdown: "## create\n\n`client.configurations.create(name: string, parameters: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }, organization_id?: string, project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; 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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: [{ name: 'x' }], product_type: 'split_v1' },\n});\n\nconsole.log(configurationResponse);\n```",
|
|
950
951
|
perLanguage: {
|
|
951
952
|
typescript: {
|
|
952
953
|
method: 'client.configurations.create',
|
|
@@ -987,7 +988,7 @@ const EMBEDDED_METHODS = [
|
|
|
987
988
|
'project_id?: string;',
|
|
988
989
|
],
|
|
989
990
|
response: "{ 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'; use_experimental_processing?: boolean; } | object; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
990
|
-
markdown: "## list\n\n`client.configurations.list(latest_only?: boolean, name?: string, organization_id?: string, page_size?: number, page_token?: string, product_type?: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'[], project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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?: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean;
|
|
991
|
+
markdown: "## list\n\n`client.configurations.list(latest_only?: boolean, name?: string, organization_id?: string, page_size?: number, page_token?: string, product_type?: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'[], project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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?: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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```",
|
|
991
992
|
perLanguage: {
|
|
992
993
|
typescript: {
|
|
993
994
|
method: 'client.configurations.list',
|
|
@@ -1020,7 +1021,7 @@ const EMBEDDED_METHODS = [
|
|
|
1020
1021
|
qualified: 'client.configurations.retrieve',
|
|
1021
1022
|
params: ['config_id: string;', 'organization_id?: string;', 'project_id?: string;'],
|
|
1022
1023
|
response: "{ 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'; use_experimental_processing?: boolean; } | object; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
1023
|
-
markdown: "## retrieve\n\n`client.configurations.retrieve(config_id: string, organization_id?: string, project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean;
|
|
1024
|
+
markdown: "## retrieve\n\n`client.configurations.retrieve(config_id: string, organization_id?: string, project_id?: string): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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```",
|
|
1024
1025
|
perLanguage: {
|
|
1025
1026
|
typescript: {
|
|
1026
1027
|
method: 'client.configurations.retrieve',
|
|
@@ -1056,10 +1057,10 @@ const EMBEDDED_METHODS = [
|
|
|
1056
1057
|
'organization_id?: string;',
|
|
1057
1058
|
'project_id?: string;',
|
|
1058
1059
|
'name?: string;',
|
|
1059
|
-
"parameters?: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean;
|
|
1060
|
+
"parameters?: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; };",
|
|
1060
1061
|
],
|
|
1061
1062
|
response: "{ 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'; use_experimental_processing?: boolean; } | object; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown'; version: string; created_at?: string; updated_at?: string; }",
|
|
1062
|
-
markdown: "## update\n\n`client.configurations.update(config_id: string, organization_id?: string, project_id?: string, name?: string, parameters?: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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?: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Updated parameters (omit to leave unchanged).\n\n### Returns\n\n- `{ id: string; name: string; parameters: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extract_version?: string; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-05-21' | '2026-04-09' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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; images_to_save?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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```",
|
|
1063
|
+
markdown: "## update\n\n`client.configurations.update(config_id: string, organization_id?: string, project_id?: string, name?: string, parameters?: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }): { id: string; name: string; parameters: split_v1_parameters | extract_v2_parameters | classify_v2_parameters | parse_v2_parameters | object | untyped_parameters; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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?: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n Updated parameters (omit to leave unchanged).\n\n### Returns\n\n- `{ id: string; name: string; parameters: { categories: split_category[]; product_type: 'split_v1'; splitting_strategy?: object; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: object[]; mode?: 'FAST'; parsing_configuration?: object; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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_configurations?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }; product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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: { categories: { name: string; description?: string; }[]; product_type: 'split_v1'; splitting_strategy?: { allow_uncategorized?: 'include' | 'forbid' | 'omit'; }; } | { data_schema: object; product_type: 'extract_v2'; cite_sources?: boolean; confidence_scores?: boolean; extraction_target?: 'per_doc' | 'per_page' | 'per_table_row'; max_pages?: number; parse_config_id?: string; parse_tier?: string; system_prompt?: string; target_pages?: string; tier?: 'cost_effective' | 'agentic'; version?: string; } | { product_type: 'classify_v2'; rules: { description: string; type: string; }[]; mode?: 'FAST'; parsing_configuration?: { lang?: string; max_pages?: number; target_pages?: string; }; } | { product_type: 'parse_v2'; tier: 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus'; version: 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' | 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; }; pdf?: object; presentation?: { 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?: 'screenshot' | 'embedded' | 'layout'[]; markdown?: { annotate_links?: boolean; inline_images?: boolean; tables?: object; }; 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; }; }; 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; }[]; cost_optimizer?: { enable?: boolean; }; disable_heuristics?: boolean; ignore?: { ignore_diagonal_text?: boolean; ignore_hidden_text?: boolean; ignore_text_in_image?: boolean; }; ocr_parameters?: { languages?: parsing_languages[]; }; specialized_chart_parsing?: 'agentic_plus' | 'agentic' | 'efficient'; }; webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: 'string' | 'json'; webhook_url?: 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'; use_experimental_processing?: boolean; } | { product_type: 'unknown'; }`\n - `product_type: 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | '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```",
|
|
1063
1064
|
perLanguage: {
|
|
1064
1065
|
typescript: {
|
|
1065
1066
|
method: 'client.configurations.update',
|
|
@@ -3907,7 +3908,7 @@ const EMBEDDED_METHODS = [
|
|
|
3907
3908
|
endpoint: '/api/v1/beta/sheets/jobs',
|
|
3908
3909
|
httpMethod: 'post',
|
|
3909
3910
|
summary: 'Create Spreadsheet Job',
|
|
3910
|
-
description: 'Create a spreadsheet parsing job.
|
|
3911
|
+
description: 'Create a spreadsheet parsing job.\n\nProvide at most one of `configuration` (an inline parsing configuration) or `configuration_id` (a saved configuration preset). If neither is provided, a default configuration is used. Optionally include `webhook_configurations` to receive `sheets.*` status notifications.\n\nExperimental: not production-ready and subject to change.',
|
|
3911
3912
|
stainlessPath: '(resource) beta.sheets > (method) create',
|
|
3912
3913
|
qualified: 'client.beta.sheets.create',
|
|
3913
3914
|
params: [
|
|
@@ -3915,9 +3916,12 @@ const EMBEDDED_METHODS = [
|
|
|
3915
3916
|
'organization_id?: string;',
|
|
3916
3917
|
'project_id?: string;',
|
|
3917
3918
|
"config?: { 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'; use_experimental_processing?: boolean; };",
|
|
3919
|
+
"configuration?: { 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'; use_experimental_processing?: boolean; };",
|
|
3920
|
+
'configuration_id?: string;',
|
|
3921
|
+
'webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[];',
|
|
3918
3922
|
],
|
|
3919
|
-
response: "{ id: string;
|
|
3920
|
-
markdown: "## create\n\n`client.beta.sheets.create(file_id: string, organization_id?: string, project_id?: string, config?: { 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'; use_experimental_processing?: boolean; }): { id: string;
|
|
3923
|
+
response: "{ id: string; configuration: object; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: object; configuration_id?: string; errors?: string[]; file?: object; metadata_state_transitions?: object; parameters?: { webhook_configurations?: object[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }",
|
|
3924
|
+
markdown: "## create\n\n`client.beta.sheets.create(file_id: string, organization_id?: string, project_id?: string, config?: { 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'; use_experimental_processing?: boolean; }, configuration?: { 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'; use_experimental_processing?: boolean; }, configuration_id?: string, webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]): { id: string; configuration: sheets_parsing_config; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: sheets_parsing_config; configuration_id?: string; errors?: string[]; file?: file; metadata_state_transitions?: object; parameters?: object; regions?: object[]; success?: boolean; worksheet_metadata?: object[]; }`\n\n**post** `/api/v1/beta/sheets/jobs`\n\nCreate a spreadsheet parsing job.\n\nProvide at most one of `configuration` (an inline parsing configuration) or `configuration_id` (a saved configuration preset). If neither is provided, a default configuration is used. Optionally include `webhook_configurations` to receive `sheets.*` status notifications.\n\nExperimental: not production-ready and subject to change.\n\n### Parameters\n\n- `file_id: string`\n The ID of the file to parse\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n- `config?: { 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'; use_experimental_processing?: boolean; }`\n Configuration for spreadsheet parsing and region extraction\n - `extraction_range?: string`\n A1 notation of the range to extract a single region from. If None, the entire sheet is used.\n - `flatten_hierarchical_tables?: boolean`\n Return a flattened dataframe when a detected table is recognized as hierarchical.\n - `generate_additional_metadata?: boolean`\n Whether to generate additional metadata (title, description) for each extracted region.\n - `include_hidden_cells?: boolean`\n Whether to include hidden cells when extracting regions from the spreadsheet.\n - `sheet_names?: string[]`\n The names of the sheets to extract regions from. If empty, all sheets will be processed.\n - `specialization?: string`\n Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline.\n - `table_merge_sensitivity?: 'strong' | 'weak'`\n Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging).\n - `use_experimental_processing?: boolean`\n Enables experimental processing. Accuracy may be impacted.\n\n- `configuration?: { 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'; use_experimental_processing?: boolean; }`\n Configuration for spreadsheet parsing and region extraction\n - `extraction_range?: string`\n A1 notation of the range to extract a single region from. If None, the entire sheet is used.\n - `flatten_hierarchical_tables?: boolean`\n Return a flattened dataframe when a detected table is recognized as hierarchical.\n - `generate_additional_metadata?: boolean`\n Whether to generate additional metadata (title, description) for each extracted region.\n - `include_hidden_cells?: boolean`\n Whether to include hidden cells when extracting regions from the spreadsheet.\n - `sheet_names?: string[]`\n The names of the sheets to extract regions from. If empty, all sheets will be processed.\n - `specialization?: string`\n Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline.\n - `table_merge_sensitivity?: 'strong' | 'weak'`\n Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging).\n - `use_experimental_processing?: boolean`\n Enables experimental processing. Accuracy may be impacted.\n\n- `configuration_id?: string`\n Saved configuration ID\n\n- `webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]`\n Outbound webhook endpoints to notify on job status changes\n\n### Returns\n\n- `{ id: string; configuration: { 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'; use_experimental_processing?: boolean; }; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: { 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'; use_experimental_processing?: boolean; }; configuration_id?: string; errors?: string[]; file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }; metadata_state_transitions?: object; parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }`\n A spreadsheet parsing job.\n\n - `id: string`\n - `configuration: { 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'; use_experimental_processing?: boolean; }`\n - `created_at: string`\n - `file_id: string`\n - `project_id: string`\n - `status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n - `updated_at: string`\n - `user_id: string`\n - `config?: { 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'; use_experimental_processing?: boolean; }`\n - `configuration_id?: string`\n - `errors?: string[]`\n - `file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }`\n - `metadata_state_transitions?: object`\n - `parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }`\n - `regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]`\n - `success?: boolean`\n - `worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst sheetsJob = await client.beta.sheets.create({ file_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' });\n\nconsole.log(sheetsJob);\n```",
|
|
3921
3925
|
perLanguage: {
|
|
3922
3926
|
typescript: {
|
|
3923
3927
|
method: 'client.beta.sheets.create',
|
|
@@ -3936,7 +3940,7 @@ const EMBEDDED_METHODS = [
|
|
|
3936
3940
|
example: "llamacloud-prod beta:sheets create \\\n --api-key 'My API Key' \\\n --file-id 182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
|
|
3937
3941
|
},
|
|
3938
3942
|
http: {
|
|
3939
|
-
example: 'curl https://api.cloud.llamaindex.ai/api/v1/beta/sheets/jobs \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"\n }\'',
|
|
3943
|
+
example: 'curl https://api.cloud.llamaindex.ai/api/v1/beta/sheets/jobs \\\n -H \'Content-Type: application/json\' \\\n -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \\\n -d \'{\n "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",\n "configuration_id": "cfg-11111111-2222-3333-4444-555555555555"\n }\'',
|
|
3940
3944
|
},
|
|
3941
3945
|
},
|
|
3942
3946
|
},
|
|
@@ -3949,6 +3953,7 @@ const EMBEDDED_METHODS = [
|
|
|
3949
3953
|
stainlessPath: '(resource) beta.sheets > (method) list',
|
|
3950
3954
|
qualified: 'client.beta.sheets.list',
|
|
3951
3955
|
params: [
|
|
3956
|
+
'configuration_id?: string;',
|
|
3952
3957
|
'created_at_on_or_after?: string;',
|
|
3953
3958
|
'created_at_on_or_before?: string;',
|
|
3954
3959
|
'include_results?: boolean;',
|
|
@@ -3959,8 +3964,8 @@ const EMBEDDED_METHODS = [
|
|
|
3959
3964
|
'project_id?: string;',
|
|
3960
3965
|
"status?: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED';",
|
|
3961
3966
|
],
|
|
3962
|
-
response: "{ id: string;
|
|
3963
|
-
markdown: "## list\n\n`client.beta.sheets.list(created_at_on_or_after?: string, created_at_on_or_before?: string, include_results?: boolean, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'): { id: string;
|
|
3967
|
+
response: "{ id: string; configuration: object; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: object; configuration_id?: string; errors?: string[]; file?: object; metadata_state_transitions?: object; parameters?: { webhook_configurations?: object[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }",
|
|
3968
|
+
markdown: "## list\n\n`client.beta.sheets.list(configuration_id?: string, created_at_on_or_after?: string, created_at_on_or_before?: string, include_results?: boolean, job_ids?: string[], organization_id?: string, page_size?: number, page_token?: string, project_id?: string, status?: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'): { id: string; configuration: sheets_parsing_config; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: sheets_parsing_config; configuration_id?: string; errors?: string[]; file?: file; metadata_state_transitions?: object; parameters?: object; regions?: object[]; success?: boolean; worksheet_metadata?: object[]; }`\n\n**get** `/api/v1/beta/sheets/jobs`\n\nList spreadsheet parsing jobs. Experimental: not production-ready and subject to change.\n\n### Parameters\n\n- `configuration_id?: string`\n Filter by saved 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- `include_results?: boolean`\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?: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n Filter by job status\n\n### Returns\n\n- `{ id: string; configuration: { 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'; use_experimental_processing?: boolean; }; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: { 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'; use_experimental_processing?: boolean; }; configuration_id?: string; errors?: string[]; file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }; metadata_state_transitions?: object; parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }`\n A spreadsheet parsing job.\n\n - `id: string`\n - `configuration: { 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'; use_experimental_processing?: boolean; }`\n - `created_at: string`\n - `file_id: string`\n - `project_id: string`\n - `status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n - `updated_at: string`\n - `user_id: string`\n - `config?: { 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'; use_experimental_processing?: boolean; }`\n - `configuration_id?: string`\n - `errors?: string[]`\n - `file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }`\n - `metadata_state_transitions?: object`\n - `parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }`\n - `regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]`\n - `success?: boolean`\n - `worksheet_metadata?: { sheet_name: string; description?: string; title?: 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 sheetsJob of client.beta.sheets.list()) {\n console.log(sheetsJob);\n}\n```",
|
|
3964
3969
|
perLanguage: {
|
|
3965
3970
|
typescript: {
|
|
3966
3971
|
method: 'client.beta.sheets.list',
|
|
@@ -3993,12 +3998,13 @@ const EMBEDDED_METHODS = [
|
|
|
3993
3998
|
qualified: 'client.beta.sheets.get',
|
|
3994
3999
|
params: [
|
|
3995
4000
|
'spreadsheet_job_id: string;',
|
|
4001
|
+
'expand?: string[];',
|
|
3996
4002
|
'include_results?: boolean;',
|
|
3997
4003
|
'organization_id?: string;',
|
|
3998
4004
|
'project_id?: string;',
|
|
3999
4005
|
],
|
|
4000
|
-
response: "{ id: string;
|
|
4001
|
-
markdown: "## get\n\n`client.beta.sheets.get(spreadsheet_job_id: string, include_results?: boolean, organization_id?: string, project_id?: string): { id: string;
|
|
4006
|
+
response: "{ id: string; configuration: object; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: object; configuration_id?: string; errors?: string[]; file?: object; metadata_state_transitions?: object; parameters?: { webhook_configurations?: object[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }",
|
|
4007
|
+
markdown: "## get\n\n`client.beta.sheets.get(spreadsheet_job_id: string, expand?: string[], include_results?: boolean, organization_id?: string, project_id?: string): { id: string; configuration: sheets_parsing_config; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: sheets_parsing_config; configuration_id?: string; errors?: string[]; file?: file; metadata_state_transitions?: object; parameters?: object; regions?: object[]; success?: boolean; worksheet_metadata?: object[]; }`\n\n**get** `/api/v1/beta/sheets/jobs/{spreadsheet_job_id}`\n\nGet a spreadsheet parsing job. When `include_results=True` (default), embeds extracted regions and results if complete, skipping the separate `/results` call. Experimental: not production-ready and subject to change.\n\n### Parameters\n\n- `spreadsheet_job_id: string`\n\n- `expand?: string[]`\n Optional fields to populate on the response. Valid values: metadata_state_transitions.\n\n- `include_results?: boolean`\n\n- `organization_id?: string`\n\n- `project_id?: string`\n\n### Returns\n\n- `{ id: string; configuration: { 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'; use_experimental_processing?: boolean; }; created_at: string; file_id: string; project_id: string; status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'; updated_at: string; user_id: string; config?: { 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'; use_experimental_processing?: boolean; }; configuration_id?: string; errors?: string[]; file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }; metadata_state_transitions?: object; parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }; regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]; success?: boolean; worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]; }`\n A spreadsheet parsing job.\n\n - `id: string`\n - `configuration: { 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'; use_experimental_processing?: boolean; }`\n - `created_at: string`\n - `file_id: string`\n - `project_id: string`\n - `status: 'PENDING' | 'SUCCESS' | 'ERROR' | 'PARTIAL_SUCCESS' | 'CANCELLED'`\n - `updated_at: string`\n - `user_id: string`\n - `config?: { 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'; use_experimental_processing?: boolean; }`\n - `configuration_id?: string`\n - `errors?: string[]`\n - `file?: { id: string; name: string; project_id: string; created_at?: string; data_source_id?: string; expires_at?: string; external_file_id?: string; file_size?: number; file_type?: string; last_modified_at?: string; permission_info?: object; purpose?: string; resource_info?: object; updated_at?: string; }`\n - `metadata_state_transitions?: object`\n - `parameters?: { webhook_configurations?: { webhook_events?: string[]; webhook_headers?: object; webhook_output_format?: string; webhook_url?: string; }[]; }`\n - `regions?: { location: string; region_type: string; sheet_name: string; description?: string; region_id?: string; title?: string; }[]`\n - `success?: boolean`\n - `worksheet_metadata?: { sheet_name: string; description?: string; title?: string; }[]`\n\n### Example\n\n```typescript\nimport LlamaCloud from '@llamaindex/llama-cloud';\n\nconst client = new LlamaCloud();\n\nconst sheetsJob = await client.beta.sheets.get('spreadsheet_job_id');\n\nconsole.log(sheetsJob);\n```",
|
|
4002
4008
|
perLanguage: {
|
|
4003
4009
|
typescript: {
|
|
4004
4010
|
method: 'client.beta.sheets.get',
|