llama-cloud 0.1.18__py3-none-any.whl → 0.1.20__py3-none-any.whl

llama_cloud/types/{base_prompt_template.py → batch_public_output.py}

@@ -4,6 +4,9 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .batch import Batch
+from .batch_item import BatchItem
+from .managed_ingestion_status_response import ManagedIngestionStatusResponse
 
 try:
     import pydantic
@@ -14,13 +17,10 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class BasePromptTemplate(pydantic.BaseModel):
-    metadata: typing.Dict[str, typing.Any]
-    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]]]
+class BatchPublicOutput(pydantic.BaseModel):
+    batch: Batch
+    batch_items: typing.List[BatchItem]
+    ingestion_status: ManagedIngestionStatusResponse
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/cloud_confluence_data_source.py

@@ -27,6 +27,7 @@ class CloudConfluenceDataSource(pydantic.BaseModel):
     cql: typing.Optional[str]
     label: typing.Optional[str]
     index_restricted_pages: typing.Optional[bool] = pydantic.Field(description="Whether to index restricted pages.")
+    keep_markdown_format: typing.Optional[bool] = pydantic.Field(description="Whether to keep the markdown format.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_jira_data_source.py

@@ -15,10 +15,6 @@ except ImportError:
 
 
 class CloudJiraDataSource(pydantic.BaseModel):
-    """
-    Cloud Jira Data Source integrating JiraReader.
-    """
-
     supports_access_control: typing.Optional[bool]
     email: typing.Optional[str]
     api_token: typing.Optional[str]

llama_cloud/types/cloud_postgres_vector_store.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .pg_vector_hnsw_settings import PgVectorHnswSettings
 
 try:
     import pydantic
@@ -26,6 +27,7 @@ class CloudPostgresVectorStore(pydantic.BaseModel):
     embed_dim: int
     hybrid_search: typing.Optional[bool]
     perform_setup: typing.Optional[bool]
+    hnsw_settings: typing.Optional[PgVectorHnswSettings]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/cloud_sharepoint_data_source.py

@@ -25,6 +25,7 @@ class CloudSharepointDataSource(pydantic.BaseModel):
     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]]
+    get_permissions: typing.Optional[bool]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/data_sink_component.py

@@ -1,7 +1,11 @@
 # This file was auto-generated by Fern from our API Definition.
 
+from __future__ import annotations
+
 import typing
 
+import typing_extensions
+
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
@@ -9,12 +13,66 @@ from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 
+
+class DataSinkComponent_AzureAiSearch(CloudAzureAiSearchVectorStore):
+    type: typing_extensions.Literal["azure_ai_search"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkComponent_Milvus(CloudMilvusVectorStore):
+    type: typing_extensions.Literal["milvus"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkComponent_MongodbAtlas(CloudMongoDbAtlasVectorSearch):
+    type: typing_extensions.Literal["mongodb_atlas"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkComponent_Pinecone(CloudPineconeVectorStore):
+    type: typing_extensions.Literal["pinecone"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkComponent_Postgres(CloudPostgresVectorStore):
+    type: typing_extensions.Literal["postgres"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkComponent_Qdrant(CloudQdrantVectorStore):
+    type: typing_extensions.Literal["qdrant"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
 DataSinkComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CloudPineconeVectorStore,
-    CloudPostgresVectorStore,
-    CloudQdrantVectorStore,
-    CloudAzureAiSearchVectorStore,
-    CloudMongoDbAtlasVectorSearch,
-    CloudMilvusVectorStore,
+    DataSinkComponent_AzureAiSearch,
+    DataSinkComponent_Milvus,
+    DataSinkComponent_MongodbAtlas,
+    DataSinkComponent_Pinecone,
+    DataSinkComponent_Postgres,
+    DataSinkComponent_Qdrant,
 ]

llama_cloud/types/data_sink_create_component.py

@@ -1,7 +1,11 @@
 # This file was auto-generated by Fern from our API Definition.
 
+from __future__ import annotations
+
 import typing
 
+import typing_extensions
+
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
@@ -9,12 +13,66 @@ from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 
+
+class DataSinkCreateComponent_AzureAiSearch(CloudAzureAiSearchVectorStore):
+    type: typing_extensions.Literal["azure_ai_search"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkCreateComponent_Milvus(CloudMilvusVectorStore):
+    type: typing_extensions.Literal["milvus"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkCreateComponent_MongodbAtlas(CloudMongoDbAtlasVectorSearch):
+    type: typing_extensions.Literal["mongodb_atlas"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkCreateComponent_Pinecone(CloudPineconeVectorStore):
+    type: typing_extensions.Literal["pinecone"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkCreateComponent_Postgres(CloudPostgresVectorStore):
+    type: typing_extensions.Literal["postgres"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSinkCreateComponent_Qdrant(CloudQdrantVectorStore):
+    type: typing_extensions.Literal["qdrant"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
 DataSinkCreateComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CloudPineconeVectorStore,
-    CloudPostgresVectorStore,
-    CloudQdrantVectorStore,
-    CloudAzureAiSearchVectorStore,
-    CloudMongoDbAtlasVectorSearch,
-    CloudMilvusVectorStore,
+    DataSinkCreateComponent_AzureAiSearch,
+    DataSinkCreateComponent_Milvus,
+    DataSinkCreateComponent_MongodbAtlas,
+    DataSinkCreateComponent_Pinecone,
+    DataSinkCreateComponent_Postgres,
+    DataSinkCreateComponent_Qdrant,
 ]

llama_cloud/types/data_source_component.py

@@ -2,27 +2,6 @@
 
 import typing
 
-from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_box_data_source import CloudBoxDataSource
-from .cloud_confluence_data_source import CloudConfluenceDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
-from .cloud_jira_data_source import CloudJiraDataSource
-from .cloud_notion_page_data_source import CloudNotionPageDataSource
-from .cloud_one_drive_data_source import CloudOneDriveDataSource
-from .cloud_s_3_data_source import CloudS3DataSource
-from .cloud_sharepoint_data_source import CloudSharepointDataSource
-from .cloud_slack_data_source import CloudSlackDataSource
+from .data_source_component_one import DataSourceComponentOne
 
-DataSourceComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CloudS3DataSource,
-    CloudAzStorageBlobDataSource,
-    CloudGoogleDriveDataSource,
-    CloudOneDriveDataSource,
-    CloudSharepointDataSource,
-    CloudSlackDataSource,
-    CloudNotionPageDataSource,
-    CloudConfluenceDataSource,
-    CloudJiraDataSource,
-    CloudBoxDataSource,
-]
+DataSourceComponent = typing.Union[typing.Dict[str, typing.Any], DataSourceComponentOne]

llama_cloud/types/data_source_component_one.py

@@ -0,0 +1,122 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
+from .cloud_confluence_data_source import CloudConfluenceDataSource
+from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
+from .cloud_one_drive_data_source import CloudOneDriveDataSource
+from .cloud_s_3_data_source import CloudS3DataSource
+from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
+
+
+class DataSourceComponentOne_AzureStorageBlob(CloudAzStorageBlobDataSource):
+    type: typing_extensions.Literal["AZURE_STORAGE_BLOB"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_Box(CloudBoxDataSource):
+    type: typing_extensions.Literal["BOX"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_Confluence(CloudConfluenceDataSource):
+    type: typing_extensions.Literal["CONFLUENCE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_GoogleDrive(CloudGoogleDriveDataSource):
+    type: typing_extensions.Literal["GOOGLE_DRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_Jira(CloudJiraDataSource):
+    type: typing_extensions.Literal["JIRA"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_MicrosoftOnedrive(CloudOneDriveDataSource):
+    type: typing_extensions.Literal["MICROSOFT_ONEDRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_MicrosoftSharepoint(CloudSharepointDataSource):
+    type: typing_extensions.Literal["MICROSOFT_SHAREPOINT"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_NotionPage(CloudNotionPageDataSource):
+    type: typing_extensions.Literal["NOTION_PAGE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_S3(CloudS3DataSource):
+    type: typing_extensions.Literal["S3"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceComponentOne_Slack(CloudSlackDataSource):
+    type: typing_extensions.Literal["SLACK"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+DataSourceComponentOne = typing.Union[
+    DataSourceComponentOne_AzureStorageBlob,
+    DataSourceComponentOne_Box,
+    DataSourceComponentOne_Confluence,
+    DataSourceComponentOne_GoogleDrive,
+    DataSourceComponentOne_Jira,
+    DataSourceComponentOne_MicrosoftOnedrive,
+    DataSourceComponentOne_MicrosoftSharepoint,
+    DataSourceComponentOne_NotionPage,
+    DataSourceComponentOne_S3,
+    DataSourceComponentOne_Slack,
+]

llama_cloud/types/data_source_create_component.py

@@ -2,27 +2,6 @@
 
 import typing
 
-from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_box_data_source import CloudBoxDataSource
-from .cloud_confluence_data_source import CloudConfluenceDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
-from .cloud_jira_data_source import CloudJiraDataSource
-from .cloud_notion_page_data_source import CloudNotionPageDataSource
-from .cloud_one_drive_data_source import CloudOneDriveDataSource
-from .cloud_s_3_data_source import CloudS3DataSource
-from .cloud_sharepoint_data_source import CloudSharepointDataSource
-from .cloud_slack_data_source import CloudSlackDataSource
+from .data_source_create_component_one import DataSourceCreateComponentOne
 
-DataSourceCreateComponent = typing.Union[
-    typing.Dict[str, typing.Any],
-    CloudS3DataSource,
-    CloudAzStorageBlobDataSource,
-    CloudGoogleDriveDataSource,
-    CloudOneDriveDataSource,
-    CloudSharepointDataSource,
-    CloudSlackDataSource,
-    CloudNotionPageDataSource,
-    CloudConfluenceDataSource,
-    CloudJiraDataSource,
-    CloudBoxDataSource,
-]
+DataSourceCreateComponent = typing.Union[typing.Dict[str, typing.Any], DataSourceCreateComponentOne]

llama_cloud/types/data_source_create_component_one.py

@@ -0,0 +1,122 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_box_data_source import CloudBoxDataSource
+from .cloud_confluence_data_source import CloudConfluenceDataSource
+from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_jira_data_source import CloudJiraDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
+from .cloud_one_drive_data_source import CloudOneDriveDataSource
+from .cloud_s_3_data_source import CloudS3DataSource
+from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
+
+
+class DataSourceCreateComponentOne_AzureStorageBlob(CloudAzStorageBlobDataSource):
+    type: typing_extensions.Literal["AZURE_STORAGE_BLOB"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_Box(CloudBoxDataSource):
+    type: typing_extensions.Literal["BOX"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_Confluence(CloudConfluenceDataSource):
+    type: typing_extensions.Literal["CONFLUENCE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_GoogleDrive(CloudGoogleDriveDataSource):
+    type: typing_extensions.Literal["GOOGLE_DRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_Jira(CloudJiraDataSource):
+    type: typing_extensions.Literal["JIRA"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_MicrosoftOnedrive(CloudOneDriveDataSource):
+    type: typing_extensions.Literal["MICROSOFT_ONEDRIVE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_MicrosoftSharepoint(CloudSharepointDataSource):
+    type: typing_extensions.Literal["MICROSOFT_SHAREPOINT"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_NotionPage(CloudNotionPageDataSource):
+    type: typing_extensions.Literal["NOTION_PAGE"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_S3(CloudS3DataSource):
+    type: typing_extensions.Literal["S3"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class DataSourceCreateComponentOne_Slack(CloudSlackDataSource):
+    type: typing_extensions.Literal["SLACK"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+DataSourceCreateComponentOne = typing.Union[
+    DataSourceCreateComponentOne_AzureStorageBlob,
+    DataSourceCreateComponentOne_Box,
+    DataSourceCreateComponentOne_Confluence,
+    DataSourceCreateComponentOne_GoogleDrive,
+    DataSourceCreateComponentOne_Jira,
+    DataSourceCreateComponentOne_MicrosoftOnedrive,
+    DataSourceCreateComponentOne_MicrosoftSharepoint,
+    DataSourceCreateComponentOne_NotionPage,
+    DataSourceCreateComponentOne_S3,
+    DataSourceCreateComponentOne_Slack,
+]

llama_cloud/types/{extract_agent_update.py → data_source_update_dispatcher_config.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
-from .extract_config import ExtractConfig
+from .delete_params import DeleteParams
 
 try:
     import pydantic
@@ -16,13 +15,14 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractAgentUpdate(pydantic.BaseModel):
+class DataSourceUpdateDispatcherConfig(pydantic.BaseModel):
     """
-    Settings for updating an extraction schema.
+    Schema for the parameters of a data source dispatcher job.
     """
 
-    data_schema: ExtractAgentUpdateDataSchema = pydantic.Field(description="The schema of the data")
-    config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+    should_delete: typing.Optional[bool]
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    delete_info: typing.Optional[DeleteParams]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/{node_parser.py → delete_params.py}

@@ -14,18 +14,16 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class NodeParser(pydantic.BaseModel):
+class DeleteParams(pydantic.BaseModel):
     """
-    Base interface for node parser.
+    Schema for the parameters of a delete job.
     """
 
-    include_metadata: typing.Optional[bool] = pydantic.Field(
-        description="Whether or not to consider metadata when splitting."
-    )
-    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]
-    class_name: typing.Optional[str]
+    document_ids_to_delete: typing.Optional[typing.List[str]]
+    files_ids_to_delete: typing.Optional[typing.List[str]]
+    data_sources_ids_to_delete: typing.Optional[typing.List[str]]
+    embed_collection_name: typing.Optional[str]
+    data_sink_id: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/{extract_agent_create.py → document_ingestion_job_params.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_agent_create_data_schema import ExtractAgentCreateDataSchema
-from .extract_config import ExtractConfig
+from .delete_params import DeleteParams
 
 try:
     import pydantic
@@ -16,14 +15,19 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractAgentCreate(pydantic.BaseModel):
+class DocumentIngestionJobParams(pydantic.BaseModel):
     """
-    Settings for creating an extraction agent.
+    Schema for the parameters of a document ingestion job.
     """
 
-    name: str = pydantic.Field(description="The name of the extraction schema")
-    data_schema: ExtractAgentCreateDataSchema = pydantic.Field(description="The schema of the data.")
-    config: ExtractConfig = pydantic.Field(description="The configuration parameters for the extraction agent.")
+    custom_metadata: typing.Optional[typing.Dict[str, typing.Any]]
+    resource_info: typing.Optional[typing.Dict[str, typing.Any]]
+    should_delete: typing.Optional[bool]
+    document_ids: typing.Optional[typing.List[str]]
+    pipeline_file_id: typing.Optional[str]
+    delete_info: typing.Optional[DeleteParams]
+    is_new_file: typing.Optional[bool] = pydantic.Field(description="Whether the file is new")
+    page_count: typing.Optional[int]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/extract_config.py

@@ -24,6 +24,8 @@ class ExtractConfig(pydantic.BaseModel):
     extraction_target: typing.Optional[ExtractTarget] = pydantic.Field(description="The extraction target specified.")
     extraction_mode: typing.Optional[ExtractMode] = pydantic.Field(description="The extraction mode specified.")
     system_prompt: typing.Optional[str]
+    use_reasoning: typing.Optional[bool] = pydantic.Field(description="Whether to use reasoning for the extraction.")
+    cite_sources: typing.Optional[bool] = pydantic.Field(description="Whether to cite sources for the extraction.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/extract_job_create.py

@@ -22,8 +22,7 @@ class ExtractJobCreate(pydantic.BaseModel):
     """
 
     extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
-    file_id: typing.Optional[str]
-    file: typing.Optional[str]
+    file_id: str = pydantic.Field(description="The id of the file")
     data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride] = pydantic.Field(
         description="The data schema to override the extraction agent's data schema with"
     )