tx_flow_analysis/venv/lib/python3.10/site-packages/openai/resources/files.py

# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

from __future__ import annotations

import time
import typing_extensions
from typing import Mapping, cast
from typing_extensions import Literal

import httpx

from .. import _legacy_response
from ..types import FilePurpose, file_list_params, file_create_params
from .._types import Body, Omit, Query, Headers, NotGiven, FileTypes, omit, not_given
from .._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
from .._compat import cached_property
from .._resource import SyncAPIResource, AsyncAPIResource
from .._response import (
    StreamedBinaryAPIResponse,
    AsyncStreamedBinaryAPIResponse,
    to_streamed_response_wrapper,
    async_to_streamed_response_wrapper,
    to_custom_streamed_response_wrapper,
    async_to_custom_streamed_response_wrapper,
)
from ..pagination import SyncCursorPage, AsyncCursorPage
from .._base_client import AsyncPaginator, make_request_options
from ..types.file_object import FileObject
from ..types.file_deleted import FileDeleted
from ..types.file_purpose import FilePurpose

__all__ = ["Files", "AsyncFiles"]


class Files(SyncAPIResource):
    @cached_property
    def with_raw_response(self) -> FilesWithRawResponse:
        """
        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/openai/openai-python#accessing-raw-response-data-eg-headers
        """
        return FilesWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> FilesWithStreamingResponse:
        """
        An alternative to `.with_raw_response` that doesn't eagerly read the response body.

        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
        """
        return FilesWithStreamingResponse(self)

    def create(
        self,
        *,
        file: FileTypes,
        purpose: FilePurpose,
        expires_after: file_create_params.ExpiresAfter | 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,
    ) -> FileObject:
        """Upload a file that can be used across various endpoints.

        Individual files can be
        up to 512 MB, and the size of all files uploaded by one organization can be up
        to 1 TB.

        - The Assistants API supports files up to 2 million tokens and of specific file
          types. See the
          [Assistants Tools guide](https://platform.openai.com/docs/assistants/tools)
          for details.
        - The Fine-tuning API only supports `.jsonl` files. The input also has certain
          required formats for fine-tuning
          [chat](https://platform.openai.com/docs/api-reference/fine-tuning/chat-input)
          or
          [completions](https://platform.openai.com/docs/api-reference/fine-tuning/completions-input)
          models.
        - The Batch API only supports `.jsonl` files up to 200 MB in size. The input
          also has a specific required
          [format](https://platform.openai.com/docs/api-reference/batch/request-input).

        Please [contact us](https://help.openai.com/) if you need to increase these
        storage limits.

        Args:
          file: The File object (not file name) to be uploaded.

          purpose: The intended purpose of the uploaded file. One of: - `assistants`: Used in the
              Assistants API - `batch`: Used in the Batch API - `fine-tune`: Used for
              fine-tuning - `vision`: Images used for vision fine-tuning - `user_data`:
              Flexible file type for any purpose - `evals`: Used for eval data sets

          expires_after: The expiration policy for a file. By default, files with `purpose=batch` expire
              after 30 days and all other files are persisted until they are manually deleted.

          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
        """
        body = deepcopy_minimal(
            {
                "file": file,
                "purpose": purpose,
                "expires_after": expires_after,
            }
        )
        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
        # It should be noted that the actual Content-Type header that will be
        # sent to the server will contain a `boundary` parameter, e.g.
        # multipart/form-data; boundary=---abc--
        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
        return self._post(
            "/files",
            body=maybe_transform(body, file_create_params.FileCreateParams),
            files=files,
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileObject,
        )

    def retrieve(
        self,
        file_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,
    ) -> FileObject:
        """
        Returns information about a specific file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return self._get(
            f"/files/{file_id}",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileObject,
        )

    def list(
        self,
        *,
        after: str | Omit = omit,
        limit: int | Omit = omit,
        order: Literal["asc", "desc"] | Omit = omit,
        purpose: 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,
    ) -> SyncCursorPage[FileObject]:
        """Returns a list of files.

        Args:
          after: A cursor for use in pagination.

        `after` is an object ID that defines your place
              in the list. For instance, if you make a list request and receive 100 objects,
              ending with obj_foo, your subsequent call can include after=obj_foo in order to
              fetch the next page of the list.

          limit: A limit on the number of objects to be returned. Limit can range between 1 and
              10,000, and the default is 10,000.

          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
              order and `desc` for descending order.

          purpose: Only return files with the given purpose.

          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
        """
        return self._get_api_list(
            "/files",
            page=SyncCursorPage[FileObject],
            options=make_request_options(
                extra_headers=extra_headers,
                extra_query=extra_query,
                extra_body=extra_body,
                timeout=timeout,
                query=maybe_transform(
                    {
                        "after": after,
                        "limit": limit,
                        "order": order,
                        "purpose": purpose,
                    },
                    file_list_params.FileListParams,
                ),
            ),
            model=FileObject,
        )

    def delete(
        self,
        file_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,
    ) -> FileDeleted:
        """
        Delete a file and remove it from all vector stores.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return self._delete(
            f"/files/{file_id}",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileDeleted,
        )

    def content(
        self,
        file_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,
    ) -> _legacy_response.HttpxBinaryResponseContent:
        """
        Returns the contents of the specified file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        extra_headers = {"Accept": "application/binary", **(extra_headers or {})}
        return self._get(
            f"/files/{file_id}/content",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=_legacy_response.HttpxBinaryResponseContent,
        )

    @typing_extensions.deprecated("The `.content()` method should be used instead")
    def retrieve_content(
        self,
        file_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,
    ) -> str:
        """
        Returns the contents of the specified file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return self._get(
            f"/files/{file_id}/content",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=str,
        )

    def wait_for_processing(
        self,
        id: str,
        *,
        poll_interval: float = 5.0,
        max_wait_seconds: float = 30 * 60,
    ) -> FileObject:
        """Waits for the given file to be processed, default timeout is 30 mins."""
        TERMINAL_STATES = {"processed", "error", "deleted"}

        start = time.time()
        file = self.retrieve(id)
        while file.status not in TERMINAL_STATES:
            self._sleep(poll_interval)

            file = self.retrieve(id)
            if time.time() - start > max_wait_seconds:
                raise RuntimeError(
                    f"Giving up on waiting for file {id} to finish processing after {max_wait_seconds} seconds."
                )

        return file


class AsyncFiles(AsyncAPIResource):
    @cached_property
    def with_raw_response(self) -> AsyncFilesWithRawResponse:
        """
        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/openai/openai-python#accessing-raw-response-data-eg-headers
        """
        return AsyncFilesWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> AsyncFilesWithStreamingResponse:
        """
        An alternative to `.with_raw_response` that doesn't eagerly read the response body.

        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
        """
        return AsyncFilesWithStreamingResponse(self)

    async def create(
        self,
        *,
        file: FileTypes,
        purpose: FilePurpose,
        expires_after: file_create_params.ExpiresAfter | 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,
    ) -> FileObject:
        """Upload a file that can be used across various endpoints.

        Individual files can be
        up to 512 MB, and the size of all files uploaded by one organization can be up
        to 1 TB.

        - The Assistants API supports files up to 2 million tokens and of specific file
          types. See the
          [Assistants Tools guide](https://platform.openai.com/docs/assistants/tools)
          for details.
        - The Fine-tuning API only supports `.jsonl` files. The input also has certain
          required formats for fine-tuning
          [chat](https://platform.openai.com/docs/api-reference/fine-tuning/chat-input)
          or
          [completions](https://platform.openai.com/docs/api-reference/fine-tuning/completions-input)
          models.
        - The Batch API only supports `.jsonl` files up to 200 MB in size. The input
          also has a specific required
          [format](https://platform.openai.com/docs/api-reference/batch/request-input).

        Please [contact us](https://help.openai.com/) if you need to increase these
        storage limits.

        Args:
          file: The File object (not file name) to be uploaded.

          purpose: The intended purpose of the uploaded file. One of: - `assistants`: Used in the
              Assistants API - `batch`: Used in the Batch API - `fine-tune`: Used for
              fine-tuning - `vision`: Images used for vision fine-tuning - `user_data`:
              Flexible file type for any purpose - `evals`: Used for eval data sets

          expires_after: The expiration policy for a file. By default, files with `purpose=batch` expire
              after 30 days and all other files are persisted until they are manually deleted.

          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
        """
        body = deepcopy_minimal(
            {
                "file": file,
                "purpose": purpose,
                "expires_after": expires_after,
            }
        )
        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
        # It should be noted that the actual Content-Type header that will be
        # sent to the server will contain a `boundary` parameter, e.g.
        # multipart/form-data; boundary=---abc--
        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
        return await self._post(
            "/files",
            body=await async_maybe_transform(body, file_create_params.FileCreateParams),
            files=files,
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileObject,
        )

    async def retrieve(
        self,
        file_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,
    ) -> FileObject:
        """
        Returns information about a specific file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return await self._get(
            f"/files/{file_id}",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileObject,
        )

    def list(
        self,
        *,
        after: str | Omit = omit,
        limit: int | Omit = omit,
        order: Literal["asc", "desc"] | Omit = omit,
        purpose: 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[FileObject, AsyncCursorPage[FileObject]]:
        """Returns a list of files.

        Args:
          after: A cursor for use in pagination.

        `after` is an object ID that defines your place
              in the list. For instance, if you make a list request and receive 100 objects,
              ending with obj_foo, your subsequent call can include after=obj_foo in order to
              fetch the next page of the list.

          limit: A limit on the number of objects to be returned. Limit can range between 1 and
              10,000, and the default is 10,000.

          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
              order and `desc` for descending order.

          purpose: Only return files with the given purpose.

          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
        """
        return self._get_api_list(
            "/files",
            page=AsyncCursorPage[FileObject],
            options=make_request_options(
                extra_headers=extra_headers,
                extra_query=extra_query,
                extra_body=extra_body,
                timeout=timeout,
                query=maybe_transform(
                    {
                        "after": after,
                        "limit": limit,
                        "order": order,
                        "purpose": purpose,
                    },
                    file_list_params.FileListParams,
                ),
            ),
            model=FileObject,
        )

    async def delete(
        self,
        file_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,
    ) -> FileDeleted:
        """
        Delete a file and remove it from all vector stores.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return await self._delete(
            f"/files/{file_id}",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=FileDeleted,
        )

    async def content(
        self,
        file_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,
    ) -> _legacy_response.HttpxBinaryResponseContent:
        """
        Returns the contents of the specified file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        extra_headers = {"Accept": "application/binary", **(extra_headers or {})}
        return await self._get(
            f"/files/{file_id}/content",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=_legacy_response.HttpxBinaryResponseContent,
        )

    @typing_extensions.deprecated("The `.content()` method should be used instead")
    async def retrieve_content(
        self,
        file_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,
    ) -> str:
        """
        Returns the contents of the specified file.

        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 file_id:
            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
        return await self._get(
            f"/files/{file_id}/content",
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=str,
        )

    async def wait_for_processing(
        self,
        id: str,
        *,
        poll_interval: float = 5.0,
        max_wait_seconds: float = 30 * 60,
    ) -> FileObject:
        """Waits for the given file to be processed, default timeout is 30 mins."""
        TERMINAL_STATES = {"processed", "error", "deleted"}

        start = time.time()
        file = await self.retrieve(id)
        while file.status not in TERMINAL_STATES:
            await self._sleep(poll_interval)

            file = await self.retrieve(id)
            if time.time() - start > max_wait_seconds:
                raise RuntimeError(
                    f"Giving up on waiting for file {id} to finish processing after {max_wait_seconds} seconds."
                )

        return file


class FilesWithRawResponse:
    def __init__(self, files: Files) -> None:
        self._files = files

        self.create = _legacy_response.to_raw_response_wrapper(
            files.create,
        )
        self.retrieve = _legacy_response.to_raw_response_wrapper(
            files.retrieve,
        )
        self.list = _legacy_response.to_raw_response_wrapper(
            files.list,
        )
        self.delete = _legacy_response.to_raw_response_wrapper(
            files.delete,
        )
        self.content = _legacy_response.to_raw_response_wrapper(
            files.content,
        )
        self.retrieve_content = (  # pyright: ignore[reportDeprecated]
            _legacy_response.to_raw_response_wrapper(
                files.retrieve_content,  # pyright: ignore[reportDeprecated],
            )
        )


class AsyncFilesWithRawResponse:
    def __init__(self, files: AsyncFiles) -> None:
        self._files = files

        self.create = _legacy_response.async_to_raw_response_wrapper(
            files.create,
        )
        self.retrieve = _legacy_response.async_to_raw_response_wrapper(
            files.retrieve,
        )
        self.list = _legacy_response.async_to_raw_response_wrapper(
            files.list,
        )
        self.delete = _legacy_response.async_to_raw_response_wrapper(
            files.delete,
        )
        self.content = _legacy_response.async_to_raw_response_wrapper(
            files.content,
        )
        self.retrieve_content = (  # pyright: ignore[reportDeprecated]
            _legacy_response.async_to_raw_response_wrapper(
                files.retrieve_content,  # pyright: ignore[reportDeprecated],
            )
        )


class FilesWithStreamingResponse:
    def __init__(self, files: Files) -> None:
        self._files = files

        self.create = to_streamed_response_wrapper(
            files.create,
        )
        self.retrieve = to_streamed_response_wrapper(
            files.retrieve,
        )
        self.list = to_streamed_response_wrapper(
            files.list,
        )
        self.delete = to_streamed_response_wrapper(
            files.delete,
        )
        self.content = to_custom_streamed_response_wrapper(
            files.content,
            StreamedBinaryAPIResponse,
        )
        self.retrieve_content = (  # pyright: ignore[reportDeprecated]
            to_streamed_response_wrapper(
                files.retrieve_content,  # pyright: ignore[reportDeprecated],
            )
        )


class AsyncFilesWithStreamingResponse:
    def __init__(self, files: AsyncFiles) -> None:
        self._files = files

        self.create = async_to_streamed_response_wrapper(
            files.create,
        )
        self.retrieve = async_to_streamed_response_wrapper(
            files.retrieve,
        )
        self.list = async_to_streamed_response_wrapper(
            files.list,
        )
        self.delete = async_to_streamed_response_wrapper(
            files.delete,
        )
        self.content = async_to_custom_streamed_response_wrapper(
            files.content,
            AsyncStreamedBinaryAPIResponse,
        )
        self.retrieve_content = (  # pyright: ignore[reportDeprecated]
            async_to_streamed_response_wrapper(
                files.retrieve_content,  # pyright: ignore[reportDeprecated],
            )
        )