llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/resources/pipelines/files.py

@@ -0,0 +1,682 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import typing_extensions
+from typing import Dict, Union, Iterable, Optional
+
+import httpx
+
+from ..._types import Body, Omit, Query, Headers, NoneType, NotGiven, omit, not_given
+from ..._utils import maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ...pagination import SyncPaginatedPipelineFiles, AsyncPaginatedPipelineFiles
+from ..._base_client import AsyncPaginator, make_request_options
+from ...types.pipelines import file_list_params, file_create_params, file_update_params, file_get_status_counts_params
+from ...types.pipelines.pipeline_file import PipelineFile
+from ...types.pipelines.file_create_response import FileCreateResponse
+from ...types.managed_ingestion_status_response import ManagedIngestionStatusResponse
+from ...types.pipelines.file_get_status_counts_response import FileGetStatusCountsResponse
+
+__all__ = ["FilesResource", "AsyncFilesResource"]
+
+
+class FilesResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> FilesResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/run-llama/llama-cloud-py#accessing-raw-response-data-eg-headers
+        """
+        return FilesResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> FilesResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/run-llama/llama-cloud-py#with_streaming_response
+        """
+        return FilesResourceWithStreamingResponse(self)
+
+    def create(
+        self,
+        pipeline_id: str,
+        *,
+        body: Iterable[file_create_params.Body],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> FileCreateResponse:
+        """
+        Add files to a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return self._put(
+            f"/api/v1/pipelines/{pipeline_id}/files",
+            body=maybe_transform(body, Iterable[file_create_params.Body]),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileCreateResponse,
+        )
+
+    def update(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        custom_metadata: Optional[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]]]
+        | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> PipelineFile:
+        """
+        Update a file for a pipeline.
+
+        Args:
+          custom_metadata: Custom metadata for the file
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return self._put(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}",
+            body=maybe_transform({"custom_metadata": custom_metadata}, file_update_params.FileUpdateParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=PipelineFile,
+        )
+
+    @typing_extensions.deprecated("deprecated")
+    def list(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: Optional[str] | Omit = omit,
+        file_name_contains: Optional[str] | Omit = omit,
+        limit: Optional[int] | Omit = omit,
+        offset: Optional[int] | Omit = omit,
+        only_manually_uploaded: bool | Omit = omit,
+        order_by: Optional[str] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> SyncPaginatedPipelineFiles[PipelineFile]:
+        """
+        Get files for a pipeline.
+
+        Args: pipeline_id: ID of the pipeline data_source_id: Optional filter by data
+        source ID only_manually_uploaded: Filter for only manually uploaded files
+        file_name_contains: Optional filter by file name (substring match) limit: Limit
+        number of results offset: Offset for pagination order_by: Field to order by
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return self._get_api_list(
+            f"/api/v1/pipelines/{pipeline_id}/files2",
+            page=SyncPaginatedPipelineFiles[PipelineFile],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "data_source_id": data_source_id,
+                        "file_name_contains": file_name_contains,
+                        "limit": limit,
+                        "offset": offset,
+                        "only_manually_uploaded": only_manually_uploaded,
+                        "order_by": order_by,
+                    },
+                    file_list_params.FileListParams,
+                ),
+            ),
+            model=PipelineFile,
+        )
+
+    def delete(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> None:
+        """
+        Delete a file from a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        extra_headers = {"Accept": "*/*", **(extra_headers or {})}
+        return self._delete(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=NoneType,
+        )
+
+    def get_status(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ManagedIngestionStatusResponse:
+        """
+        Get status of a file for a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return self._get(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}/status",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ManagedIngestionStatusResponse,
+        )
+
+    def get_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: Optional[str] | Omit = omit,
+        only_manually_uploaded: bool | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> FileGetStatusCountsResponse:
+        """
+        Get files for a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return self._get(
+            f"/api/v1/pipelines/{pipeline_id}/files/status-counts",
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "data_source_id": data_source_id,
+                        "only_manually_uploaded": only_manually_uploaded,
+                    },
+                    file_get_status_counts_params.FileGetStatusCountsParams,
+                ),
+            ),
+            cast_to=FileGetStatusCountsResponse,
+        )
+
+
+class AsyncFilesResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncFilesResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/run-llama/llama-cloud-py#accessing-raw-response-data-eg-headers
+        """
+        return AsyncFilesResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncFilesResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/run-llama/llama-cloud-py#with_streaming_response
+        """
+        return AsyncFilesResourceWithStreamingResponse(self)
+
+    async def create(
+        self,
+        pipeline_id: str,
+        *,
+        body: Iterable[file_create_params.Body],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> FileCreateResponse:
+        """
+        Add files to a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return await self._put(
+            f"/api/v1/pipelines/{pipeline_id}/files",
+            body=await async_maybe_transform(body, Iterable[file_create_params.Body]),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileCreateResponse,
+        )
+
+    async def update(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        custom_metadata: Optional[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]]]
+        | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> PipelineFile:
+        """
+        Update a file for a pipeline.
+
+        Args:
+          custom_metadata: Custom metadata for the file
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return await self._put(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}",
+            body=await async_maybe_transform({"custom_metadata": custom_metadata}, file_update_params.FileUpdateParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=PipelineFile,
+        )
+
+    @typing_extensions.deprecated("deprecated")
+    def list(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: Optional[str] | Omit = omit,
+        file_name_contains: Optional[str] | Omit = omit,
+        limit: Optional[int] | Omit = omit,
+        offset: Optional[int] | Omit = omit,
+        only_manually_uploaded: bool | Omit = omit,
+        order_by: Optional[str] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> AsyncPaginator[PipelineFile, AsyncPaginatedPipelineFiles[PipelineFile]]:
+        """
+        Get files for a pipeline.
+
+        Args: pipeline_id: ID of the pipeline data_source_id: Optional filter by data
+        source ID only_manually_uploaded: Filter for only manually uploaded files
+        file_name_contains: Optional filter by file name (substring match) limit: Limit
+        number of results offset: Offset for pagination order_by: Field to order by
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return self._get_api_list(
+            f"/api/v1/pipelines/{pipeline_id}/files2",
+            page=AsyncPaginatedPipelineFiles[PipelineFile],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "data_source_id": data_source_id,
+                        "file_name_contains": file_name_contains,
+                        "limit": limit,
+                        "offset": offset,
+                        "only_manually_uploaded": only_manually_uploaded,
+                        "order_by": order_by,
+                    },
+                    file_list_params.FileListParams,
+                ),
+            ),
+            model=PipelineFile,
+        )
+
+    async def delete(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> None:
+        """
+        Delete a file from a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        extra_headers = {"Accept": "*/*", **(extra_headers or {})}
+        return await self._delete(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=NoneType,
+        )
+
+    async def get_status(
+        self,
+        file_id: str,
+        *,
+        pipeline_id: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ManagedIngestionStatusResponse:
+        """
+        Get status of a file for a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return await self._get(
+            f"/api/v1/pipelines/{pipeline_id}/files/{file_id}/status",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ManagedIngestionStatusResponse,
+        )
+
+    async def get_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: Optional[str] | Omit = omit,
+        only_manually_uploaded: bool | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> FileGetStatusCountsResponse:
+        """
+        Get files for a pipeline.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not pipeline_id:
+            raise ValueError(f"Expected a non-empty value for `pipeline_id` but received {pipeline_id!r}")
+        return await self._get(
+            f"/api/v1/pipelines/{pipeline_id}/files/status-counts",
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=await async_maybe_transform(
+                    {
+                        "data_source_id": data_source_id,
+                        "only_manually_uploaded": only_manually_uploaded,
+                    },
+                    file_get_status_counts_params.FileGetStatusCountsParams,
+                ),
+            ),
+            cast_to=FileGetStatusCountsResponse,
+        )
+
+
+class FilesResourceWithRawResponse:
+    def __init__(self, files: FilesResource) -> None:
+        self._files = files
+
+        self.create = to_raw_response_wrapper(
+            files.create,
+        )
+        self.update = to_raw_response_wrapper(
+            files.update,
+        )
+        self.list = (  # pyright: ignore[reportDeprecated]
+            to_raw_response_wrapper(
+                files.list,  # pyright: ignore[reportDeprecated],
+            )
+        )
+        self.delete = to_raw_response_wrapper(
+            files.delete,
+        )
+        self.get_status = to_raw_response_wrapper(
+            files.get_status,
+        )
+        self.get_status_counts = to_raw_response_wrapper(
+            files.get_status_counts,
+        )
+
+
+class AsyncFilesResourceWithRawResponse:
+    def __init__(self, files: AsyncFilesResource) -> None:
+        self._files = files
+
+        self.create = async_to_raw_response_wrapper(
+            files.create,
+        )
+        self.update = async_to_raw_response_wrapper(
+            files.update,
+        )
+        self.list = (  # pyright: ignore[reportDeprecated]
+            async_to_raw_response_wrapper(
+                files.list,  # pyright: ignore[reportDeprecated],
+            )
+        )
+        self.delete = async_to_raw_response_wrapper(
+            files.delete,
+        )
+        self.get_status = async_to_raw_response_wrapper(
+            files.get_status,
+        )
+        self.get_status_counts = async_to_raw_response_wrapper(
+            files.get_status_counts,
+        )
+
+
+class FilesResourceWithStreamingResponse:
+    def __init__(self, files: FilesResource) -> None:
+        self._files = files
+
+        self.create = to_streamed_response_wrapper(
+            files.create,
+        )
+        self.update = to_streamed_response_wrapper(
+            files.update,
+        )
+        self.list = (  # pyright: ignore[reportDeprecated]
+            to_streamed_response_wrapper(
+                files.list,  # pyright: ignore[reportDeprecated],
+            )
+        )
+        self.delete = to_streamed_response_wrapper(
+            files.delete,
+        )
+        self.get_status = to_streamed_response_wrapper(
+            files.get_status,
+        )
+        self.get_status_counts = to_streamed_response_wrapper(
+            files.get_status_counts,
+        )
+
+
+class AsyncFilesResourceWithStreamingResponse:
+    def __init__(self, files: AsyncFilesResource) -> None:
+        self._files = files
+
+        self.create = async_to_streamed_response_wrapper(
+            files.create,
+        )
+        self.update = async_to_streamed_response_wrapper(
+            files.update,
+        )
+        self.list = (  # pyright: ignore[reportDeprecated]
+            async_to_streamed_response_wrapper(
+                files.list,  # pyright: ignore[reportDeprecated],
+            )
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            files.delete,
+        )
+        self.get_status = async_to_streamed_response_wrapper(
+            files.get_status,
+        )
+        self.get_status_counts = async_to_streamed_response_wrapper(
+            files.get_status_counts,
+        )