CallbackManagerForLLMRun#

class langchain_core.callbacks.manager.CallbackManagerForLLMRun(*, run_id: UUID, handlers: list[BaseCallbackHandler], inheritable_handlers: list[BaseCallbackHandler], parent_run_id: UUID | None = None, tags: list[str] | None = None, inheritable_tags: list[str] | None = None, metadata: dict[str, Any] | None = None, inheritable_metadata: dict[str, Any] | None = None)[source]#

Callback manager for LLM run.

Initialize the run manager.

Parameters:

  • run_id (UUID) – The ID of the run.

  • handlers (List[BaseCallbackHandler]) – The list of handlers.

  • inheritable_handlers (List[BaseCallbackHandler]) – The list of inheritable handlers.

  • parent_run_id (UUID, optional) – The ID of the parent run. Defaults to None.

  • tags (Optional[List[str]]) – The list of tags. Defaults to None.

  • inheritable_tags (Optional[List[str]]) – The list of inheritable tags. Defaults to None.

  • metadata (Optional[Dict[str, Any]]) – The metadata. Defaults to None.

  • inheritable_metadata (Optional[Dict[str, Any]]) – The inheritable metadata. Defaults to None.

Methods

__init__(*, run_id, handlers, ...[, ...])

Initialize the run manager.

get_noop_manager()

Return a manager that doesn't perform any operations.

on_custom_event(name, data, *, run_id[, ...])

Override to define a handler for a custom event.

on_llm_end(response, **kwargs)

Run when LLM ends running.

on_llm_error(error, **kwargs)

Run when LLM errors.

on_llm_new_token(token, *[, chunk])

Run when LLM generates a new token.

on_retry(retry_state, **kwargs)

Run when a retry is received.

on_text(text, **kwargs)

Run when a text is received.
__init__(*, run_id: UUID, handlers: list[BaseCallbackHandler], inheritable_handlers: list[BaseCallbackHandler], parent_run_id: UUID | None = None, tags: list[str] | None = None, inheritable_tags: list[str] | None = None, metadata: dict[str, Any] | None = None, inheritable_metadata: dict[str, Any] | None = None) → None#

Initialize the run manager.

Parameters:

  • run_id (UUID) – The ID of the run.

  • handlers (List[BaseCallbackHandler]) – The list of handlers.

  • inheritable_handlers (List[BaseCallbackHandler]) – The list of inheritable handlers.

  • parent_run_id (UUID, optional) – The ID of the parent run. Defaults to None.

  • tags (Optional[List[str]]) – The list of tags. Defaults to None.

  • inheritable_tags (Optional[List[str]]) – The list of inheritable tags. Defaults to None.

  • metadata (Optional[Dict[str, Any]]) – The metadata. Defaults to None.

  • inheritable_metadata (Optional[Dict[str, Any]]) – The inheritable metadata. Defaults to None.

Return type:

None

classmethod get_noop_manager() → BRM#

Return a manager that doesn’t perform any operations.

Returns:

The noop manager.

Return type:

BaseRunManager

on_custom_event(name: str, data: Any, *, run_id: UUID, tags: list[str] | None = None, metadata: dict[str, Any] | None = None, **kwargs: Any) → Any#

Override to define a handler for a custom event.

Parameters:

  • name (str) – The name of the custom event.

  • data (Any) – The data for the custom event. Format will match the format specified by the user.

  • run_id (UUID) – The ID of the run.

  • tags (list[str] | None) – The tags associated with the custom event (includes inherited tags).

  • metadata (dict[str, Any] | None) – The metadata associated with the custom event (includes inherited metadata).

  • kwargs (Any)

Return type:

Any

Added in version 0.2.15.

on_llm_end(response: LLMResult, **kwargs: Any) → None[source]#

Run when LLM ends running.

Parameters:

  • response (LLMResult) – The LLM result.

  • **kwargs (Any) – Additional keyword arguments.

Return type:

None

on_llm_error(error: BaseException, **kwargs: Any) → None[source]#

Run when LLM errors.

Parameters:

  • error (Exception or KeyboardInterrupt) – The error.

  • kwargs (Any) –

    Additional keyword arguments. - response (LLMResult): The response which was generated before

    the error occurred.

Return type:

None

on_llm_new_token(token: str, *, chunk: GenerationChunk | ChatGenerationChunk | None = None, **kwargs: Any) → None[source]#

Run when LLM generates a new token.

Parameters:

  • token (str) – The new token.

  • chunk (Optional[Union[GenerationChunk, ChatGenerationChunk]], optional) – The chunk. Defaults to None.

  • **kwargs (Any) – Additional keyword arguments.

Return type:

None

on_retry(retry_state: RetryCallState, **kwargs: Any) → None#

Run when a retry is received.

Parameters:

  • retry_state (RetryCallState) – The retry state.

  • **kwargs (Any) – Additional keyword arguments.

Return type:

None

on_text(text: str, **kwargs: Any) → Any#

Run when a text is received.

Parameters:

  • text (str) – The received text.

  • **kwargs (Any) – Additional keyword arguments.

Returns:

The result of the callback.

Return type:

Any

Examples using CallbackManagerForLLMRun