AsyncMessages Class — anthropic-sdk-python Architecture

Source Code

src/anthropic/resources/messages/messages.py lines 1495–2909

class AsyncMessages(AsyncAPIResource):
    @cached_property
    def batches(self) -> AsyncBatches:
        return AsyncBatches(self._client)

    @cached_property
    def with_raw_response(self) -> AsyncMessagesWithRawResponse:
        """
        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/anthropics/anthropic-sdk-python#accessing-raw-response-data-eg-headers
        """
        return AsyncMessagesWithRawResponse(self)

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

        For more information, see https://www.github.com/anthropics/anthropic-sdk-python#with_streaming_response
        """
        return AsyncMessagesWithStreamingResponse(self)

    @overload
    async def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[MessageParam],
        model: ModelParam,
        inference_geo: Optional[str] | Omit = omit,
        metadata: MetadataParam | Omit = omit,
        output_config: OutputConfigParam | Omit = omit,
        service_tier: Literal["auto", "standard_only"] | Omit = omit,
        stop_sequences: SequenceNotStr[str] | Omit = omit,
        stream: Literal[False] | Omit = omit,
        system: Union[str, Iterable[TextBlockParam]] | Omit = omit,
        temperature: float | Omit = omit,
        thinking: ThinkingConfigParam | Omit = omit,
        tool_choice: ToolChoiceParam | Omit = omit,
        tools: Iterable[ToolUnionParam] | Omit = omit,
        top_k: int | Omit = omit,
        top_p: float | 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,
    ) -> Message:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Learn more about the Messages API in our
        [user guide](https://docs.claude.com/en/docs/initial-setup)

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.claude.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.