llama-cloud 0.1.5__py3-none-any.whl → 0.1.6__py3-none-any.whl

llama_cloud/types/__init__.py

@@ -55,12 +55,10 @@ from .configurable_transformation_names import ConfigurableTransformationNames
 from .configured_transformation_item import ConfiguredTransformationItem
 from .configured_transformation_item_component import ConfiguredTransformationItemComponent
 from .data_sink import DataSink
-from .data_sink_component import DataSinkComponent
 from .data_sink_create import DataSinkCreate
 from .data_sink_create_component import DataSinkCreateComponent
 from .data_sink_definition import DataSinkDefinition
 from .data_source import DataSource
-from .data_source_component import DataSourceComponent
 from .data_source_create import DataSourceCreate
 from .data_source_create_component import DataSourceCreateComponent
 from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
@@ -104,6 +102,7 @@ from .extraction_result_data_value import ExtractionResultDataValue
 from .extraction_schema import ExtractionSchema
 from .extraction_schema_data_schema_value import ExtractionSchemaDataSchemaValue
 from .file import File
+from .file_permission_info_value import FilePermissionInfoValue
 from .file_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
 from .filter_operator import FilterOperator
@@ -112,7 +111,6 @@ from .gemini_embedding_config import GeminiEmbeddingConfig
 from .http_validation_error import HttpValidationError
 from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
 from .hugging_face_inference_api_embedding_config import HuggingFaceInferenceApiEmbeddingConfig
-from .hugging_face_inference_api_embedding_token import HuggingFaceInferenceApiEmbeddingToken
 from .ingestion_error_response import IngestionErrorResponse
 from .input_message import InputMessage
 from .interval_usage_and_plan import IntervalUsageAndPlan
@@ -132,7 +130,6 @@ from .markdown_node_parser import MarkdownNodeParser
 from .message_annotation import MessageAnnotation
 from .message_role import MessageRole
 from .metadata_filter import MetadataFilter
-from .metadata_filter_value import MetadataFilterValue
 from .metadata_filters import MetadataFilters
 from .metadata_filters_filters_item import MetadataFiltersFiltersItem
 from .metric_result import MetricResult
@@ -155,6 +152,7 @@ from .parsing_history_item import ParsingHistoryItem
 from .parsing_job import ParsingJob
 from .parsing_job_json_result import ParsingJobJsonResult
 from .parsing_job_markdown_result import ParsingJobMarkdownResult
+from .parsing_job_structured_result import ParsingJobStructuredResult
 from .parsing_job_text_result import ParsingJobTextResult
 from .parsing_usage import ParsingUsage
 from .partition_names import PartitionNames
@@ -174,7 +172,6 @@ from .pipeline_create_embedding_config import (
 )
 from .pipeline_create_transform_config import PipelineCreateTransformConfig
 from .pipeline_data_source import PipelineDataSource
-from .pipeline_data_source_component import PipelineDataSourceComponent
 from .pipeline_data_source_create import PipelineDataSourceCreate
 from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
 from .pipeline_deployment import PipelineDeployment
@@ -193,6 +190,7 @@ from .pipeline_file_config_hash_value import PipelineFileConfigHashValue
 from .pipeline_file_create import PipelineFileCreate
 from .pipeline_file_create_custom_metadata_value import PipelineFileCreateCustomMetadataValue
 from .pipeline_file_custom_metadata_value import PipelineFileCustomMetadataValue
+from .pipeline_file_permission_info_value import PipelineFilePermissionInfoValue
 from .pipeline_file_resource_info_value import PipelineFileResourceInfoValue
 from .pipeline_transform_config import (
     PipelineTransformConfig,
@@ -223,6 +221,7 @@ from .supported_llm_model_names import SupportedLlmModelNames
 from .text_node import TextNode
 from .text_node_relationships_value import TextNodeRelationshipsValue
 from .text_node_with_score import TextNodeWithScore
+from .token import Token
 from .token_chunking_config import TokenChunkingConfig
 from .token_text_splitter import TokenTextSplitter
 from .transformation_category_names import TransformationCategoryNames
@@ -233,6 +232,7 @@ from .user_organization_delete import UserOrganizationDelete
 from .user_organization_role import UserOrganizationRole
 from .validation_error import ValidationError
 from .validation_error_loc_item import ValidationErrorLocItem
+from .value import Value
 from .vertex_ai_embedding_config import VertexAiEmbeddingConfig
 from .vertex_embedding_mode import VertexEmbeddingMode
 from .vertex_text_embedding import VertexTextEmbedding
@@ -289,12 +289,10 @@ __all__ = [
     "ConfiguredTransformationItem",
     "ConfiguredTransformationItemComponent",
     "DataSink",
-    "DataSinkComponent",
     "DataSinkCreate",
     "DataSinkCreateComponent",
     "DataSinkDefinition",
     "DataSource",
-    "DataSourceComponent",
     "DataSourceCreate",
     "DataSourceCreateComponent",
     "DataSourceCreateCustomMetadataValue",
@@ -334,6 +332,7 @@ __all__ = [
     "ExtractionSchema",
     "ExtractionSchemaDataSchemaValue",
     "File",
+    "FilePermissionInfoValue",
     "FileResourceInfoValue",
     "FilterCondition",
     "FilterOperator",
@@ -342,7 +341,6 @@ __all__ = [
     "HttpValidationError",
     "HuggingFaceInferenceApiEmbedding",
     "HuggingFaceInferenceApiEmbeddingConfig",
-    "HuggingFaceInferenceApiEmbeddingToken",
     "IngestionErrorResponse",
     "InputMessage",
     "IntervalUsageAndPlan",
@@ -362,7 +360,6 @@ __all__ = [
     "MessageAnnotation",
     "MessageRole",
     "MetadataFilter",
-    "MetadataFilterValue",
     "MetadataFilters",
     "MetadataFiltersFiltersItem",
     "MetricResult",
@@ -385,6 +382,7 @@ __all__ = [
     "ParsingJob",
     "ParsingJobJsonResult",
     "ParsingJobMarkdownResult",
+    "ParsingJobStructuredResult",
     "ParsingJobTextResult",
     "ParsingUsage",
     "PartitionNames",
@@ -402,7 +400,6 @@ __all__ = [
     "PipelineCreateEmbeddingConfig_VertexaiEmbedding",
     "PipelineCreateTransformConfig",
     "PipelineDataSource",
-    "PipelineDataSourceComponent",
     "PipelineDataSourceCreate",
     "PipelineDataSourceCustomMetadataValue",
     "PipelineDeployment",
@@ -419,6 +416,7 @@ __all__ = [
     "PipelineFileCreate",
     "PipelineFileCreateCustomMetadataValue",
     "PipelineFileCustomMetadataValue",
+    "PipelineFilePermissionInfoValue",
     "PipelineFileResourceInfoValue",
     "PipelineTransformConfig",
     "PipelineTransformConfig_Advanced",
@@ -447,6 +445,7 @@ __all__ = [
     "TextNode",
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",
+    "Token",
     "TokenChunkingConfig",
     "TokenTextSplitter",
     "TransformationCategoryNames",
@@ -457,6 +456,7 @@ __all__ = [
     "UserOrganizationRole",
     "ValidationError",
     "ValidationErrorLocItem",
+    "Value",
     "VertexAiEmbeddingConfig",
     "VertexEmbeddingMode",
     "VertexTextEmbedding",

llama_cloud/types/azure_open_ai_embedding.py

@@ -17,22 +17,28 @@ except ImportError:
 class AzureOpenAiEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The name of the OpenAI embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the OpenAI API."
     )
-    api_key: typing.Optional[str]
+    api_key: typing.Optional[str] = pydantic.Field(description="The OpenAI API key.")
     api_base: typing.Optional[str] = pydantic.Field(description="The base URL for Azure deployment.")
     api_version: typing.Optional[str] = pydantic.Field(description="The version for Azure OpenAI API.")
     max_retries: typing.Optional[int] = pydantic.Field(description="Maximum number of retries.")
     timeout: typing.Optional[float] = pydantic.Field(description="Timeout for each request.")
-    default_headers: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    default_headers: typing.Optional[typing.Dict[str, typing.Optional[str]]] = pydantic.Field(
+        description="The default headers for API requests."
+    )
     reuse_client: typing.Optional[bool] = pydantic.Field(
         description="Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability."
     )
-    dimensions: typing.Optional[int]
-    azure_endpoint: typing.Optional[str]
-    azure_deployment: typing.Optional[str]
+    dimensions: typing.Optional[int] = pydantic.Field(
+        description="The number of dimensions on the output embedding vectors. Works only with v3 embedding models."
+    )
+    azure_endpoint: typing.Optional[str] = pydantic.Field(description="The Azure endpoint to use.")
+    azure_deployment: typing.Optional[str] = pydantic.Field(description="The Azure deployment to use.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/base_prompt_template.py

@@ -19,8 +19,12 @@ class BasePromptTemplate(pydantic.BaseModel):
     template_vars: typing.List[str]
     kwargs: typing.Dict[str, str]
     output_parser: typing.Any
-    template_var_mappings: typing.Optional[typing.Dict[str, typing.Any]]
-    function_mappings: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    template_var_mappings: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
+        description="Template variable mappings (Optional)."
+    )
+    function_mappings: typing.Optional[typing.Dict[str, typing.Optional[str]]] = pydantic.Field(
+        description="Function mappings (Optional). This is a mapping from template variable names to functions that take in the current kwargs and return a string."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/bedrock_embedding.py

@@ -17,12 +17,18 @@ except ImportError:
 class BedrockEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Bedrock model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
-    profile_name: typing.Optional[str]
-    aws_access_key_id: typing.Optional[str]
-    aws_secret_access_key: typing.Optional[str]
-    aws_session_token: typing.Optional[str]
-    region_name: typing.Optional[str]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
+    profile_name: typing.Optional[str] = pydantic.Field(
+        description="The name of aws profile to use. If not given, then the default profile is used."
+    )
+    aws_access_key_id: typing.Optional[str] = pydantic.Field(description="AWS Access Key ID to use")
+    aws_secret_access_key: typing.Optional[str] = pydantic.Field(description="AWS Secret Access Key to use")
+    aws_session_token: typing.Optional[str] = pydantic.Field(description="AWS Session Token to use")
+    region_name: typing.Optional[str] = pydantic.Field(
+        description="AWS region name to use. Uses region configured in AWS CLI if not passed"
+    )
     max_retries: typing.Optional[int] = pydantic.Field(description="The maximum number of API retries.")
     timeout: typing.Optional[float] = pydantic.Field(
         description="The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts."

llama_cloud/types/character_splitter.py

@@ -24,12 +24,14 @@ class CharacterSplitter(pydantic.BaseModel):
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
     chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
     separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
     paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
-    secondary_chunking_regex: typing.Optional[str]
+    secondary_chunking_regex: typing.Optional[str] = pydantic.Field(
+        description="Backup regex for splitting into sentences."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/chat_message.py

@@ -23,7 +23,7 @@ class ChatMessage(pydantic.BaseModel):
         description="Retrieval annotations for the message."
     )
     role: MessageRole
-    content: typing.Optional[str]
+    content: typing.Optional[str] = pydantic.Field(description="Text content of the generation")
     additional_kwargs: typing.Optional[typing.Dict[str, str]] = pydantic.Field(
         description="Additional arguments passed to the model"
     )

llama_cloud/types/cloud_az_storage_blob_data_source.py

@@ -15,15 +15,24 @@ except ImportError:
 
 
 class CloudAzStorageBlobDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     container_name: str = pydantic.Field(description="The name of the Azure Storage Blob container to read from.")
     account_url: str = pydantic.Field(description="The Azure Storage Blob account URL to use for authentication.")
-    blob: typing.Optional[str]
-    prefix: typing.Optional[str]
-    account_name: typing.Optional[str]
-    account_key: typing.Optional[str]
-    tenant_id: typing.Optional[str]
-    client_id: typing.Optional[str]
-    client_secret: typing.Optional[str]
+    blob: typing.Optional[str] = pydantic.Field(description="The blob name to read from.")
+    prefix: typing.Optional[str] = pydantic.Field(
+        description="The prefix of the Azure Storage Blob objects to read from."
+    )
+    account_name: typing.Optional[str] = pydantic.Field(
+        description="The Azure Storage Blob account name to use for authentication."
+    )
+    account_key: typing.Optional[str] = pydantic.Field(
+        description="The Azure Storage Blob account key to use for authentication."
+    )
+    tenant_id: typing.Optional[str] = pydantic.Field(description="The Azure AD tenant ID to use for authentication.")
+    client_id: typing.Optional[str] = pydantic.Field(description="The Azure AD client ID to use for authentication.")
+    client_secret: typing.Optional[str] = pydantic.Field(
+        description="The Azure AD client secret to use for authentication."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_box_data_source.py

@@ -16,15 +16,22 @@ except ImportError:
 
 
 class CloudBoxDataSource(pydantic.BaseModel):
-    folder_id: typing.Optional[str]
+    supports_access_control: typing.Optional[bool]
+    folder_id: typing.Optional[str] = pydantic.Field(description="The ID of the Box folder to read from.")
     authentication_mechanism: BoxAuthMechanism = pydantic.Field(
         description="The type of authentication to use (Developer Token or CCG)"
     )
-    developer_token: typing.Optional[str]
-    client_id: typing.Optional[str]
-    client_secret: typing.Optional[str]
-    user_id: typing.Optional[str]
-    enterprise_id: typing.Optional[str]
+    developer_token: typing.Optional[str] = pydantic.Field(
+        description="Developer token for authentication if authentication_mechanism is 'developer_token'."
+    )
+    client_id: typing.Optional[str] = pydantic.Field(
+        description="Box API key used for identifying the application the user is authenticating with"
+    )
+    client_secret: typing.Optional[str] = pydantic.Field(description="Box API secret used for making auth requests.")
+    user_id: typing.Optional[str] = pydantic.Field(description="Box User ID, if provided authenticates as user.")
+    enterprise_id: typing.Optional[str] = pydantic.Field(
+        description="Box Enterprise ID, if provided authenticates as service."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_confluence_data_source.py

@@ -15,16 +15,17 @@ except ImportError:
 
 
 class CloudConfluenceDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     server_url: str = pydantic.Field(description="The server URL of the Confluence instance.")
     authentication_mechanism: str = pydantic.Field(
         description="Type of Authentication for connecting to Confluence APIs."
     )
-    user_name: typing.Optional[str]
-    api_token: typing.Optional[str]
-    space_key: typing.Optional[str]
-    page_ids: typing.Optional[str]
-    cql: typing.Optional[str]
-    label: typing.Optional[str]
+    user_name: typing.Optional[str] = pydantic.Field(description="The username to use for authentication.")
+    api_token: typing.Optional[str] = pydantic.Field(description="The API token to use for authentication.")
+    space_key: typing.Optional[str] = pydantic.Field(description="The space key to read from.")
+    page_ids: typing.Optional[str] = pydantic.Field(description="The page IDs of the Confluence to read from.")
+    cql: typing.Optional[str] = pydantic.Field(description="The CQL query to use for fetching pages.")
+    label: typing.Optional[str] = pydantic.Field(description="The label to use for fetching pages.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_document.py

@@ -23,7 +23,9 @@ class CloudDocument(pydantic.BaseModel):
     metadata: typing.Dict[str, typing.Any]
     excluded_embed_metadata_keys: typing.Optional[typing.List[str]]
     excluded_llm_metadata_keys: typing.Optional[typing.List[str]]
-    page_positions: typing.Optional[typing.List[int]]
+    page_positions: typing.Optional[typing.List[int]] = pydantic.Field(
+        description="indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]."
+    )
     id: str
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_document_create.py

@@ -23,7 +23,9 @@ class CloudDocumentCreate(pydantic.BaseModel):
     metadata: typing.Dict[str, typing.Any]
     excluded_embed_metadata_keys: typing.Optional[typing.List[str]]
     excluded_llm_metadata_keys: typing.Optional[typing.List[str]]
-    page_positions: typing.Optional[typing.List[int]]
+    page_positions: typing.Optional[typing.List[int]] = pydantic.Field(
+        description="indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]."
+    )
     id: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_google_drive_data_source.py

@@ -15,6 +15,7 @@ except ImportError:
 
 
 class CloudGoogleDriveDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     folder_id: str = pydantic.Field(description="The ID of the Google Drive folder to read from.")
     service_account_key: typing.Dict[str, typing.Any] = pydantic.Field(
         description="The service account key JSON to use for authentication."

llama_cloud/types/cloud_jira_data_source.py

@@ -19,10 +19,13 @@ class CloudJiraDataSource(pydantic.BaseModel):
     Cloud Jira Data Source integrating JiraReader.
     """
 
-    email: typing.Optional[str]
-    api_token: typing.Optional[str]
-    server_url: typing.Optional[str]
-    cloud_id: typing.Optional[str]
+    supports_access_control: typing.Optional[bool]
+    email: typing.Optional[str] = pydantic.Field(description="The email address to use for authentication.")
+    api_token: typing.Optional[str] = pydantic.Field(
+        description="The API/ Access Token used for Basic, PAT and OAuth2 authentication."
+    )
+    server_url: typing.Optional[str] = pydantic.Field(description="The server url for Jira Cloud.")
+    cloud_id: typing.Optional[str] = pydantic.Field(description="The cloud ID, used in case of OAuth2.")
     authentication_mechanism: str = pydantic.Field(description="Type of Authentication for connecting to Jira APIs.")
     query: str = pydantic.Field(description="JQL (Jira Query Language) query to search.")
     class_name: typing.Optional[str]

llama_cloud/types/cloud_notion_page_data_source.py

@@ -15,9 +15,10 @@ except ImportError:
 
 
 class CloudNotionPageDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     integration_token: str = pydantic.Field(description="The integration token to use for authentication.")
-    database_ids: typing.Optional[str]
-    page_ids: typing.Optional[str]
+    database_ids: typing.Optional[str] = pydantic.Field(description="The Notion Database Id to read content from.")
+    page_ids: typing.Optional[str] = pydantic.Field(description="The Page ID's of the Notion to read from.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_one_drive_data_source.py

@@ -15,13 +15,16 @@ except ImportError:
 
 
 class CloudOneDriveDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     user_principal_name: str = pydantic.Field(description="The user principal name to use for authentication.")
-    folder_path: typing.Optional[str]
-    folder_id: typing.Optional[str]
+    folder_path: typing.Optional[str] = pydantic.Field(description="The path of the OneDrive folder to read from.")
+    folder_id: typing.Optional[str] = pydantic.Field(description="The ID of the OneDrive folder to read from.")
     client_id: str = pydantic.Field(description="The client ID to use for authentication.")
     client_secret: str = pydantic.Field(description="The client secret to use for authentication.")
     tenant_id: str = pydantic.Field(description="The tenant ID to use for authentication.")
-    required_exts: typing.Optional[typing.List[str]]
+    required_exts: typing.Optional[typing.List[str]] = pydantic.Field(
+        description="The list of required file extensions."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_s_3_data_source.py

@@ -15,11 +15,16 @@ except ImportError:
 
 
 class CloudS3DataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     bucket: str = pydantic.Field(description="The name of the S3 bucket to read from.")
-    prefix: typing.Optional[str]
-    aws_access_id: typing.Optional[str]
-    aws_access_secret: typing.Optional[str]
-    s_3_endpoint_url: typing.Optional[str] = pydantic.Field(alias="s3_endpoint_url")
+    prefix: typing.Optional[str] = pydantic.Field(description="The prefix of the S3 objects to read from.")
+    aws_access_id: typing.Optional[str] = pydantic.Field(description="The AWS access ID to use for authentication.")
+    aws_access_secret: typing.Optional[str] = pydantic.Field(
+        description="The AWS access secret to use for authentication."
+    )
+    s_3_endpoint_url: typing.Optional[str] = pydantic.Field(
+        alias="s3_endpoint_url", description="The S3 endpoint URL to use for authentication."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_sharepoint_data_source.py

@@ -15,15 +15,18 @@ except ImportError:
 
 
 class CloudSharepointDataSource(pydantic.BaseModel):
-    site_name: typing.Optional[str]
-    site_id: typing.Optional[str]
-    folder_path: typing.Optional[str]
-    folder_id: typing.Optional[str]
-    drive_name: typing.Optional[str]
+    supports_access_control: typing.Optional[bool]
+    site_name: typing.Optional[str] = pydantic.Field(description="The name of the SharePoint site to download from.")
+    site_id: typing.Optional[str] = pydantic.Field(description="The ID of the SharePoint site to download from.")
+    folder_path: typing.Optional[str] = pydantic.Field(description="The path of the Sharepoint folder to read from.")
+    folder_id: typing.Optional[str] = pydantic.Field(description="The ID of the Sharepoint folder to read from.")
+    drive_name: typing.Optional[str] = pydantic.Field(description="The name of the Sharepoint drive to read from.")
     client_id: str = pydantic.Field(description="The client ID to use for authentication.")
     client_secret: str = pydantic.Field(description="The client secret to use for authentication.")
     tenant_id: str = pydantic.Field(description="The tenant ID to use for authentication.")
-    required_exts: typing.Optional[typing.List[str]]
+    required_exts: typing.Optional[typing.List[str]] = pydantic.Field(
+        description="The list of required file extensions."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_slack_data_source.py

@@ -15,13 +15,14 @@ except ImportError:
 
 
 class CloudSlackDataSource(pydantic.BaseModel):
+    supports_access_control: typing.Optional[bool]
     slack_token: str = pydantic.Field(description="Slack Bot Token.")
-    channel_ids: typing.Optional[str]
-    latest_date: typing.Optional[str]
-    earliest_date: typing.Optional[str]
-    earliest_date_timestamp: typing.Optional[float]
-    latest_date_timestamp: typing.Optional[float]
-    channel_patterns: typing.Optional[str]
+    channel_ids: typing.Optional[str] = pydantic.Field(description="Slack Channel.")
+    latest_date: typing.Optional[str] = pydantic.Field(description="Latest date.")
+    earliest_date: typing.Optional[str] = pydantic.Field(description="Earliest date.")
+    earliest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Earliest date timestamp.")
+    latest_date_timestamp: typing.Optional[float] = pydantic.Field(description="Latest date timestamp.")
+    channel_patterns: typing.Optional[str] = pydantic.Field(description="Slack Channel name pattern.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/code_splitter.py

@@ -27,7 +27,7 @@ class CodeSplitter(pydantic.BaseModel):
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     language: str = pydantic.Field(description="The programming language of the code being split.")
     chunk_lines: typing.Optional[int] = pydantic.Field(description="The number of lines to include in each chunk.")
     chunk_lines_overlap: typing.Optional[int] = pydantic.Field(

llama_cloud/types/cohere_embedding.py

@@ -17,10 +17,14 @@ except ImportError:
 class CohereEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Cohere model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
-    api_key: typing.Optional[str]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
+    api_key: typing.Optional[str] = pydantic.Field(description="The Cohere API key.")
     truncate: typing.Optional[str] = pydantic.Field(description="Truncation type - START/ END/ NONE")
-    input_type: typing.Optional[str]
+    input_type: typing.Optional[str] = pydantic.Field(
+        description="Model Input type. If not provided, search_document and search_query are used when needed."
+    )
     embedding_type: typing.Optional[str] = pydantic.Field(
         description="Embedding type. If not provided float embedding_type is used when needed."
     )

llama_cloud/types/data_sink.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_sink_names import ConfigurableDataSinkNames
-from .data_sink_component import DataSinkComponent
+from .data_sink_create_component import DataSinkCreateComponent
 
 try:
     import pydantic
@@ -22,11 +22,11 @@ class DataSink(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="The name of the data sink.")
     sink_type: ConfigurableDataSinkNames
-    component: DataSinkComponent
+    component: DataSinkCreateComponent = pydantic.Field(description="Component that implements the data sink")
     project_id: str
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_sink_create.py

@@ -23,7 +23,7 @@ class DataSinkCreate(pydantic.BaseModel):
 
     name: str = pydantic.Field(description="The name of the data sink.")
     sink_type: ConfigurableDataSinkNames
-    component: DataSinkCreateComponent
+    component: DataSinkCreateComponent = pydantic.Field(description="Component that implements the data sink")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/data_source.py

@@ -5,7 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .configurable_data_source_names import ConfigurableDataSourceNames
-from .data_source_component import DataSourceComponent
+from .data_source_create_component import DataSourceCreateComponent
 from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
 
 try:
@@ -23,12 +23,14 @@ class DataSource(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCustomMetadataValue]]]
-    component: DataSourceComponent
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCustomMetadataValue]]] = pydantic.Field(
+        description="Custom metadata that will be present on all data loaded from the data source"
+    )
+    component: DataSourceCreateComponent = pydantic.Field(description="Component that implements the data source")
     project_id: str
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_source_create.py

@@ -24,8 +24,10 @@ class DataSourceCreate(pydantic.BaseModel):
 
     name: str = pydantic.Field(description="The name of the data source.")
     source_type: ConfigurableDataSourceNames
-    custom_metadata: typing.Optional[typing.Dict[str, typing.Optional[DataSourceCreateCustomMetadataValue]]]
-    component: DataSourceCreateComponent
+    custom_metadata: typing.Optional[
+        typing.Dict[str, typing.Optional[DataSourceCreateCustomMetadataValue]]
+    ] = pydantic.Field(description="Custom metadata that will be present on all data loaded from the data source")
+    component: DataSourceCreateComponent = pydantic.Field(description="Component that implements the data source")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/embedding_model_config.py

@@ -21,8 +21,8 @@ class EmbeddingModelConfig(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="The name of the embedding model config.")
     embedding_config: EmbeddingModelConfigEmbeddingConfig = pydantic.Field(
         description="The embedding configuration for the embedding model config."

llama_cloud/types/embedding_model_config_update.py

@@ -16,8 +16,10 @@ except ImportError:
 
 
 class EmbeddingModelConfigUpdate(pydantic.BaseModel):
-    name: typing.Optional[str]
-    embedding_config: typing.Optional[EmbeddingModelConfigUpdateEmbeddingConfig]
+    name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model config.")
+    embedding_config: typing.Optional[EmbeddingModelConfigUpdateEmbeddingConfig] = pydantic.Field(
+        description="The embedding configuration for the embedding model config."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}