Menu

Overview Caches Callbacks Documents Document loaders Embeddings Exceptions Language models Serialization Output parsers Prompts Rate limiters Retrievers Runnables Utilities Vector stores

Language

Theme

Class●Since v0.1

AsyncCallbackManagerForLLMRun

Async callback manager for LLM run.

AsyncCallbackManagerForLLMRun(
  self,
  *,
  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
)

Bases

AsyncRunManagerLLMManagerMixin

Methods

Get the equivalent sync RunManager.

on_llm_new_token

Run when LLM generates a new token.

Run when LLM ends running.

Run when LLM errors.

Inherited fromAsyncRunManager

Methods

Run on an arbitrary text.

Run on retry.

Inherited fromBaseRunManager

Attributes

A unique identifier for the model or chain run.

Ahandlers: handlers Ainheritable_handlers: inheritable_handlers Aparent_run_id: UUID | None

The ID of the parent run.

Atags: list[str] | None

Optional list of tags associated with the retriever.

Ainheritable_tags Ametadata: dict[str, Any] | None

Optional metadata associated with the retriever.

Ainheritable_metadata

Methods

Mget_noop_manager

Return a manager that doesn't perform any operations.

Inherited fromRunManagerMixin

Methods

Run on an arbitrary text.

Run on retry.

Mon_custom_event

Generate a custom astream event.

View source on GitHub