guardrails_ai.sdk.chat_completions_api
======================================

.. py:module:: guardrails_ai.sdk.chat_completions_api


Classes
-------

.. autoapisummary::

   guardrails_ai.sdk.chat_completions_api.ChatApi
   guardrails_ai.sdk.chat_completions_api.CompletionsApi
   guardrails_ai.sdk.chat_completions_api.GuardedChatCompletion
   guardrails_ai.sdk.chat_completions_api.GuardedChatCompletionChunk


Module Contents
---------------

.. py:class:: ChatApi(*, http_client: httpx.AsyncClient, headers: dict[str, str], max_retries: int)

   Bases: :py:obj:`guardrails_ai.sdk.abstract_client.Client`


   Namespaced chat API, mirroring the OpenAI ``chat`` namespace.

   Accessed via ``client.guards.chat``.


   .. py:attribute:: completions
      :type:  CompletionsApi


   .. py:attribute:: headers
      :type:  dict[str, str]


   .. py:attribute:: http_client
      :type:  httpx.AsyncClient


   .. py:attribute:: max_retries
      :type:  int


.. py:class:: CompletionsApi(*, http_client: httpx.AsyncClient, headers: dict[str, str], max_retries: int)

   Bases: :py:obj:`guardrails_ai.sdk.abstract_client.Client`


   Guarded chat completions, mirroring the OpenAI completions API.

   Accessed via ``client.guards.chat.completions``.


   .. py:method:: create(guard_id: str, **kwargs: Unpack[openai.types.chat.completion_create_params.CompletionCreateParamsStreaming]) -> openai.AsyncStream[GuardedChatCompletionChunk]
                  create(guard_id: str, **kwargs: Unpack[openai.types.chat.completion_create_params.CompletionCreateParamsNonStreaming]) -> GuardedChatCompletion
      :async:


      Create a guarded chat completion.

      Proxies the request through the Guardrails API so that the response is
      validated by the named Guard before being returned to the caller.

      :param guard_id: The unique id of the Guard to apply to the completion.
      :param stream: If ``True``, returns an async stream of ``GuardedChatCompletionChunk``
                     objects. Defaults to ``False``.
      :param \*\*kwargs: Additional keyword arguments forwarded to the OpenAI
                         ``chat.completions.create`` call (e.g. ``model``, ``messages``).

      :returns: A ``GuardedChatCompletion`` when ``stream=False``, or an
                ``AsyncStream[GuardedChatCompletionChunk]`` when ``stream=True``.

      Example::

          # Non-streaming
          response = await client.guards.chat.completions.create(
              guard_id="xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx",
              model="gpt-4o-mini",
              messages=[{"role": "user", "content": "Hello!"}],
          )

          # Streaming
          async for chunk in await client.guards.chat.completions.create(
              guard_id="xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx",
              model="gpt-4o-mini",
              messages=[{"role": "user", "content": "Hello!"}],
              stream=True,
          ):
              print(chunk)



   .. py:attribute:: headers
      :type:  dict[str, str]


   .. py:attribute:: http_client
      :type:  httpx.AsyncClient


   .. py:attribute:: max_retries
      :type:  int


.. py:class:: GuardedChatCompletion

   Bases: :py:obj:`openai.types.chat.ChatCompletion`


   .. py:attribute:: guardrails
      :type:  Optional[guardrails_ai.types.ValidationOutcome]


.. py:class:: GuardedChatCompletionChunk

   Bases: :py:obj:`openai.types.chat.ChatCompletionChunk`


   .. py:attribute:: guardrails
      :type:  Optional[guardrails_ai.types.ValidationOutcome]