Method agenerate

libs/core/langchain_core/language_models/llms.py:898–1065

Asynchronously pass a sequence of prompts to a model and return generations. This method should make use of batched calls for models that expose a batched API. Use this method when you want to: 1. take advantage of batched calls, 2. need more output

(
        self,
        prompts: List[str],
        stop: Optional[List[str]] = None,
        callbacks: Optional[Union[Callbacks, List[Callbacks]]] = None,
        *,
        tags: Optional[Union[List[str], List[List[str]]]] = None,
        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
        run_name: Optional[Union[str, List[str]]] = None,
        run_id: Optional[Union[uuid.UUID, List[Optional[uuid.UUID]]]] = None,
        **kwargs: Any,
    )

        return output

    async def agenerate(
        self,
        prompts: List[str],
        stop: Optional[List[str]] = None,
        callbacks: Optional[Union[Callbacks, List[Callbacks]]] = None,
        *,
        tags: Optional[Union[List[str], List[List[str]]]] = None,
        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
        run_name: Optional[Union[str, List[str]]] = None,
        run_id: Optional[Union[uuid.UUID, List[Optional[uuid.UUID]]]] = None,
        **kwargs: Any,
    ) -> LLMResult:
        """Asynchronously pass a sequence of prompts to a model and return generations.

        This method should make use of batched calls for models that expose a batched
        API.

        Use this method when you want to:
            1. take advantage of batched calls,
            2. need more output from the model than just the top generated value,
            3. are building chains that are agnostic to the underlying language model
                type (e.g., pure text completion models vs chat models).

        Args:
            prompts: List of string prompts.
            stop: Stop words to use when generating. Model output is cut off at the
                first occurrence of any of these substrings.
            callbacks: Callbacks to pass through. Used for executing additional
                functionality, such as logging or streaming, throughout generation.
            **kwargs: Arbitrary additional keyword arguments. These are usually passed
                to the model provider API call.

        Returns:
            An LLMResult, which contains a list of candidate Generations for each input
                prompt and additional model provider-specific output.
        """
        # Create callback managers
        if isinstance(callbacks, list) and (
            isinstance(callbacks[0], (list, BaseCallbackManager))
            or callbacks[0] is None
        ):
            # We've received a list of callbacks args to apply to each input
            assert len(callbacks) == len(prompts)
            assert tags is None or (
                isinstance(tags, list) and len(tags) == len(prompts)
            )
            assert metadata is None or (
                isinstance(metadata, list) and len(metadata) == len(prompts)
            )
            assert run_name is None or (
                isinstance(run_name, list) and len(run_name) == len(prompts)
            )
            callbacks = cast(List[Callbacks], callbacks)
            tags_list = cast(List[Optional[List[str]]], tags or ([None] * len(prompts)))
            metadata_list = cast(
                List[Optional[Dict[str, Any]]], metadata or ([{}] * len(prompts))
            )
            run_name_list = run_name or cast(