llama-cloud 0.0.7__py3-none-any.whl → 0.0.8__py3-none-any.whl

llama_cloud/resources/pipelines/client.py

@@ -644,12 +644,22 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def list_pipeline_files(self, pipeline_id: str) -> typing.List[PipelineFile]:
+    def list_pipeline_files(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> typing.List[PipelineFile]:
         """
         Get files for a pipeline.
 
         Parameters:
             - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -663,6 +673,9 @@ class PipelinesClient:
         _response = self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files"),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -837,6 +850,65 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def import_pipeline_metadata(self, pipeline_id: str, *, upload_file: typing.IO) -> typing.Dict[str, str]:
+        """
+        Import metadata for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - upload_file: typing.IO.
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/metadata"),
+            data=jsonable_encoder({}),
+            files={"upload_file": upload_file},
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Dict[str, str], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def delete_pipeline_files_metadata(self, pipeline_id: str) -> None:
+        """
+        Delete metadata for all files in a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.pipelines.delete_pipeline_files_metadata(
+            pipeline_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/metadata"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def list_pipeline_data_sources(self, pipeline_id: str) -> typing.List[PipelineDataSource]:
         """
         Get data sources for a pipeline.
@@ -1968,12 +2040,22 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def list_pipeline_files(self, pipeline_id: str) -> typing.List[PipelineFile]:
+    async def list_pipeline_files(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> typing.List[PipelineFile]:
         """
         Get files for a pipeline.
 
         Parameters:
             - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1987,6 +2069,9 @@ class AsyncPipelinesClient:
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files"),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -2161,6 +2246,65 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def import_pipeline_metadata(self, pipeline_id: str, *, upload_file: typing.IO) -> typing.Dict[str, str]:
+        """
+        Import metadata for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - upload_file: typing.IO.
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/metadata"),
+            data=jsonable_encoder({}),
+            files={"upload_file": upload_file},
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Dict[str, str], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def delete_pipeline_files_metadata(self, pipeline_id: str) -> None:
+        """
+        Delete metadata for all files in a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.pipelines.delete_pipeline_files_metadata(
+            pipeline_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/metadata"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def list_pipeline_data_sources(self, pipeline_id: str) -> typing.List[PipelineDataSource]:
         """
         Get data sources for a pipeline.

llama_cloud/types/__init__.py

@@ -6,17 +6,18 @@ from .base_prompt_template import BasePromptTemplate
 from .bedrock_embedding import BedrockEmbedding
 from .chat_message import ChatMessage
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_document import CloudDocument
 from .cloud_document_create import CloudDocumentCreate
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+from .cloud_notion_page_data_source import CloudNotionPageDataSource
 from .cloud_one_drive_data_source import CloudOneDriveDataSource
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 from .cloud_s_3_data_source import CloudS3DataSource
 from .cloud_sharepoint_data_source import CloudSharepointDataSource
+from .cloud_slack_data_source import CloudSlackDataSource
 from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 from .code_splitter import CodeSplitter
 from .cohere_embedding import CohereEmbedding
@@ -52,6 +53,10 @@ from .eval_llm_model_data import EvalLlmModelData
 from .eval_question import EvalQuestion
 from .eval_question_create import EvalQuestionCreate
 from .eval_question_result import EvalQuestionResult
+from .extraction_result import ExtractionResult
+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_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
@@ -132,17 +137,18 @@ __all__ = [
     "BedrockEmbedding",
     "ChatMessage",
     "CloudAzStorageBlobDataSource",
+    "CloudAzureAiSearchVectorStore",
     "CloudChromaVectorStore",
     "CloudDocument",
     "CloudDocumentCreate",
-    "CloudGcsDataSource",
-    "CloudGoogleDriveDataSource",
+    "CloudNotionPageDataSource",
     "CloudOneDriveDataSource",
     "CloudPineconeVectorStore",
     "CloudPostgresVectorStore",
     "CloudQdrantVectorStore",
     "CloudS3DataSource",
     "CloudSharepointDataSource",
+    "CloudSlackDataSource",
     "CloudWeaviateVectorStore",
     "CodeSplitter",
     "CohereEmbedding",
@@ -178,6 +184,10 @@ __all__ = [
     "EvalQuestion",
     "EvalQuestionCreate",
     "EvalQuestionResult",
+    "ExtractionResult",
+    "ExtractionResultDataValue",
+    "ExtractionSchema",
+    "ExtractionSchemaDataSchemaValue",
     "File",
     "FileResourceInfoValue",
     "FilterCondition",

llama_cloud/types/azure_open_ai_embedding.py

@@ -62,6 +62,9 @@ class AzureOpenAiEmbedding(pydantic.BaseModel):
     )
     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.")
+    use_azure_ad: bool = pydantic.Field(
+        description="Indicates if Microsoft Entra ID (former Azure AD) is used for token authentication"
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/{cloud_gcs_data_source.py → cloud_azure_ai_search_vector_store.py}

@@ -14,16 +14,18 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class CloudGcsDataSource(pydantic.BaseModel):
+class CloudAzureAiSearchVectorStore(pydantic.BaseModel):
     """
-    Base component object to capture class names.
+    Cloud Azure AI Search Vector Store.
     """
 
-    bucket: str = pydantic.Field(description="The name of the GCS bucket to read from.")
-    prefix: typing.Optional[str] = pydantic.Field(description="The prefix of the GCS objects to read from.")
-    service_account_key: typing.Dict[str, typing.Any] = pydantic.Field(
-        description="The service account key JSON to use for authentication."
-    )
+    supports_nested_metadata_filters: typing.Optional[bool]
+    search_service_api_key: str
+    search_service_endpoint: str
+    search_service_api_version: typing.Optional[str]
+    index_name: typing.Optional[str]
+    filterable_metadata_field_keys: typing.Optional[typing.List[str]]
+    embedding_dimension: typing.Optional[int]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/{cloud_google_drive_data_source.py → cloud_notion_page_data_source.py}

@@ -14,15 +14,14 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class CloudGoogleDriveDataSource(pydantic.BaseModel):
+class CloudNotionPageDataSource(pydantic.BaseModel):
     """
     Base component object to capture class names.
     """
 
-    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."
-    )
+    integration_token: str = pydantic.Field(description="The integration token to use for authentication.")
+    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_slack_data_source.py

@@ -0,0 +1,42 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class CloudSlackDataSource(pydantic.BaseModel):
+    """
+    Base component object to capture class names.
+    """
+
+    slack_token: str = pydantic.Field(description="Slack Bot Token.")
+    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:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/configurable_data_sink_names.py

@@ -16,6 +16,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
     POSTGRES = "POSTGRES"
     QDRANT = "QDRANT"
     WEAVIATE = "WEAVIATE"
+    AZUREAI_SEARCH = "AZUREAI_SEARCH"
 
     def visit(
         self,
@@ -24,6 +25,7 @@ class ConfigurableDataSinkNames(str, enum.Enum):
         postgres: typing.Callable[[], T_Result],
         qdrant: typing.Callable[[], T_Result],
         weaviate: typing.Callable[[], T_Result],
+        azureai_search: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSinkNames.CHROMA:
             return chroma()
@@ -35,3 +37,5 @@ class ConfigurableDataSinkNames(str, enum.Enum):
             return qdrant()
         if self is ConfigurableDataSinkNames.WEAVIATE:
             return weaviate()
+        if self is ConfigurableDataSinkNames.AZUREAI_SEARCH:
+            return azureai_search()

llama_cloud/types/configurable_data_source_names.py

@@ -13,29 +13,29 @@ class ConfigurableDataSourceNames(str, enum.Enum):
 
     S_3 = "S3"
     AZURE_STORAGE_BLOB = "AZURE_STORAGE_BLOB"
-    GCS = "GCS"
-    GOOGLE_DRIVE = "GOOGLE_DRIVE"
     MICROSOFT_ONEDRIVE = "MICROSOFT_ONEDRIVE"
     MICROSOFT_SHAREPOINT = "MICROSOFT_SHAREPOINT"
+    SLACK = "SLACK"
+    NOTION_PAGE = "NOTION_PAGE"
 
     def visit(
         self,
         s_3: typing.Callable[[], T_Result],
         azure_storage_blob: typing.Callable[[], T_Result],
-        gcs: typing.Callable[[], T_Result],
-        google_drive: typing.Callable[[], T_Result],
         microsoft_onedrive: typing.Callable[[], T_Result],
         microsoft_sharepoint: typing.Callable[[], T_Result],
+        slack: typing.Callable[[], T_Result],
+        notion_page: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableDataSourceNames.S_3:
             return s_3()
         if self is ConfigurableDataSourceNames.AZURE_STORAGE_BLOB:
             return azure_storage_blob()
-        if self is ConfigurableDataSourceNames.GCS:
-            return gcs()
-        if self is ConfigurableDataSourceNames.GOOGLE_DRIVE:
-            return google_drive()
         if self is ConfigurableDataSourceNames.MICROSOFT_ONEDRIVE:
             return microsoft_onedrive()
         if self is ConfigurableDataSourceNames.MICROSOFT_SHAREPOINT:
             return microsoft_sharepoint()
+        if self is ConfigurableDataSourceNames.SLACK:
+            return slack()
+        if self is ConfigurableDataSourceNames.NOTION_PAGE:
+            return notion_page()

llama_cloud/types/data_sink_component_one.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
@@ -14,4 +15,5 @@ DataSinkComponentOne = typing.Union[
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
 ]

llama_cloud/types/data_sink_create_component_one.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
@@ -14,4 +15,5 @@ DataSinkCreateComponentOne = typing.Union[
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
     CloudWeaviateVectorStore,
+    CloudAzureAiSearchVectorStore,
 ]

llama_cloud/types/data_source_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+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
 
 DataSourceComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/data_source_create_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+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
 
 DataSourceCreateComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/extraction_result.py

@@ -0,0 +1,42 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .extraction_result_data_value import ExtractionResultDataValue
+from .file import File
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractionResult(pydantic.BaseModel):
+    """
+    Schema for an extraction result.
+    """
+
+    id: str = pydantic.Field(description="Unique identifier")
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
+    schema_id: str = pydantic.Field(description="The id of the schema")
+    data: typing.Dict[str, ExtractionResultDataValue] = pydantic.Field(description="The data extracted from the file")
+    file: File = pydantic.Field(description="The file that the extract was extracted from")
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/extraction_result_data_value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractionResultDataValue = typing.Union[typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool]

llama_cloud/types/extraction_schema.py

@@ -0,0 +1,44 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .extraction_schema_data_schema_value import ExtractionSchemaDataSchemaValue
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractionSchema(pydantic.BaseModel):
+    """
+    Schema for extraction schema.
+    """
+
+    id: str = pydantic.Field(description="Unique identifier")
+    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 extraction schema")
+    project_id: str = pydantic.Field(description="The ID of the project that the extraction schema belongs to")
+    data_schema: typing.Dict[str, ExtractionSchemaDataSchemaValue] = pydantic.Field(
+        description="The schema of the data"
+    )
+    openai_api_key: str = pydantic.Field(description="The API key for the OpenAI API")
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

llama_cloud/types/extraction_schema_data_schema_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractionSchemaDataSchemaValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]

llama_cloud/types/pipeline_data_source_component_one.py

@@ -3,17 +3,17 @@
 import typing
 
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
-from .cloud_gcs_data_source import CloudGcsDataSource
-from .cloud_google_drive_data_source import CloudGoogleDriveDataSource
+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
 
 PipelineDataSourceComponentOne = typing.Union[
     CloudS3DataSource,
     CloudAzStorageBlobDataSource,
-    CloudGcsDataSource,
-    CloudGoogleDriveDataSource,
     CloudOneDriveDataSource,
     CloudSharepointDataSource,
+    CloudSlackDataSource,
+    CloudNotionPageDataSource,
 ]

llama_cloud/types/text_node.py

@@ -37,6 +37,7 @@ class TextNode(pydantic.BaseModel):
         description="A mapping of relationships to other node information."
     )
     text: typing.Optional[str] = pydantic.Field(description="Text content of the node.")
+    mimetype: typing.Optional[str] = pydantic.Field(description="MIME type of the node content.")
     start_char_idx: typing.Optional[int] = pydantic.Field(description="Start char index of the node.")
     end_char_idx: typing.Optional[int] = pydantic.Field(description="End char index of the node.")
     text_template: typing.Optional[str] = pydantic.Field(

{llama_cloud-0.0.7.dist-info → llama_cloud-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.0.7
+Version: 0.0.8
 Summary: 
 Author: Logan Markewich
 Author-email: logan@runllama.ai
@@ -10,7 +10,6 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: httpx (>=0.20.0)
 Requires-Dist: pydantic (>=1.10)
 Description-Content-Type: text/markdown