langchain.callbacks.streaming_aiter_final_only.AsyncFinalIteratorCallbackHandler¶

class langchain.callbacks.streaming_aiter_final_only.AsyncFinalIteratorCallbackHandler(*, answer_prefix_tokens: Optional[List[str]] = None, strip_tokens: bool = True, stream_prefix: bool = False)[source]¶

Callback handler that returns an async iterator. Only the final output of the agent will be iterated.

Instantiate AsyncFinalIteratorCallbackHandler.

Parameters
  • answer_prefix_tokens (Optional[List[str]]) – Token sequence that prefixes the answer. Default is [“Final”, “Answer”, “:”]

  • strip_tokens (bool) – Ignore white spaces and new lines when comparing answer_prefix_tokens to last tokens? (to determine if answer has been reached)

  • stream_prefix (bool) – Should answer prefix itself also be streamed?

Attributes

always_verbose

ignore_agent

Whether to ignore agent callbacks.

ignore_chain

Whether to ignore chain callbacks.

ignore_chat_model

Whether to ignore chat model callbacks.

ignore_llm

Whether to ignore LLM callbacks.

ignore_retriever

Whether to ignore retriever callbacks.

ignore_retry

Whether to ignore retry callbacks.

raise_error

run_inline

Methods

__init__(*[, answer_prefix_tokens, ...])

Instantiate AsyncFinalIteratorCallbackHandler.

aiter()

append_to_last_tokens(token)

check_if_answer_reached()

on_agent_action(action, *, run_id[, ...])

Run on agent action.

on_agent_finish(finish, *, run_id[, ...])

Run on agent end.

on_chain_end(outputs, *, run_id[, ...])

Run when chain ends running.

on_chain_error(error, *, run_id[, ...])

Run when chain errors.

on_chain_start(serialized, inputs, *, run_id)

Run when chain starts running.

on_chat_model_start(serialized, messages, *, ...)

Run when a chat model starts running.

on_llm_end(response, **kwargs)

Run when LLM ends running.

on_llm_error(error, **kwargs)

Run when LLM errors.

on_llm_new_token(token, **kwargs)

Run on new LLM token.

on_llm_start(serialized, prompts, **kwargs)

Run when LLM starts running.

on_retriever_end(documents, *, run_id[, ...])

Run on retriever end.

on_retriever_error(error, *, run_id[, ...])

Run on retriever error.

on_retriever_start(serialized, query, *, run_id)

Run on retriever start.

on_retry(retry_state, *, run_id[, parent_run_id])

Run on a retry event.

on_text(text, *, run_id[, parent_run_id, tags])

Run on arbitrary text.

on_tool_end(output, *, run_id[, ...])

Run when tool ends running.

on_tool_error(error, *, run_id[, ...])

Run when tool errors.

on_tool_start(serialized, input_str, *, run_id)

Run when tool starts running.

__init__(*, answer_prefix_tokens: Optional[List[str]] = None, strip_tokens: bool = True, stream_prefix: bool = False) None[source]¶

Instantiate AsyncFinalIteratorCallbackHandler.

Parameters
  • answer_prefix_tokens (Optional[List[str]]) – Token sequence that prefixes the answer. Default is [“Final”, “Answer”, “:”]

  • strip_tokens (bool) – Ignore white spaces and new lines when comparing answer_prefix_tokens to last tokens? (to determine if answer has been reached)

  • stream_prefix (bool) – Should answer prefix itself also be streamed?

Return type

None

async aiter() AsyncIterator[str]¶
Return type

AsyncIterator[str]

append_to_last_tokens(token: str) None[source]¶
Parameters

token (str) –

Return type

None

check_if_answer_reached() bool[source]¶
Return type

bool

async on_agent_action(action: AgentAction, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run on agent action.

Parameters
  • action (AgentAction) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_agent_finish(finish: AgentFinish, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run on agent end.

Parameters
  • finish (AgentFinish) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_chain_end(outputs: Dict[str, Any], *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run when chain ends running.

Parameters
  • outputs (Dict[str, Any]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_chain_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run when chain errors.

Parameters
  • error (BaseException) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_chain_start(serialized: Dict[str, Any], inputs: Dict[str, Any], *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) None¶

Run when chain starts running.

Parameters
  • serialized (Dict[str, Any]) –

  • inputs (Dict[str, Any]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • kwargs (Any) –

Return type

None

async on_chat_model_start(serialized: Dict[str, Any], messages: List[List[BaseMessage]], *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) Any¶

Run when a chat model starts running.

ATTENTION: This method is called for chat models. If you’re implementing

a handler for a non-chat model, you should use on_llm_start instead.

Parameters
  • serialized (Dict[str, Any]) –

  • messages (List[List[BaseMessage]]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • kwargs (Any) –

Return type

Any

async on_llm_end(response: LLMResult, **kwargs: Any) None[source]¶

Run when LLM ends running.

Parameters
  • response (LLMResult) –

  • kwargs (Any) –

Return type

None

async on_llm_error(error: BaseException, **kwargs: Any) None¶

Run when LLM errors.

Parameters
  • error (BaseException) – The error that occurred.

  • kwargs (Any) –

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

    the error occurred.

Return type

None

async on_llm_new_token(token: str, **kwargs: Any) None[source]¶

Run on new LLM token. Only available when streaming is enabled.

Parameters
  • token (str) –

  • kwargs (Any) –

Return type

None

async on_llm_start(serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) None[source]¶

Run when LLM starts running.

ATTENTION: This method is called for non-chat models (regular LLMs). If

you’re implementing a handler for a chat model, you should use on_chat_model_start instead.

Parameters
  • serialized (Dict[str, Any]) –

  • prompts (List[str]) –

  • kwargs (Any) –

Return type

None

async on_retriever_end(documents: Sequence[Document], *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run on retriever end.

Parameters
  • documents (Sequence[Document]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run on retriever error.

Parameters
  • error (BaseException) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_retriever_start(serialized: Dict[str, Any], query: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) None¶

Run on retriever start.

Parameters
  • serialized (Dict[str, Any]) –

  • query (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • kwargs (Any) –

Return type

None

async on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any¶

Run on a retry event.

Parameters
  • retry_state (RetryCallState) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

async on_text(text: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run on arbitrary text.

Parameters
  • text (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_tool_end(output: Any, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run when tool ends running.

Parameters
  • output (Any) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_tool_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None¶

Run when tool errors.

Parameters
  • error (BaseException) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • kwargs (Any) –

Return type

None

async on_tool_start(serialized: Dict[str, Any], input_str: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, inputs: Optional[Dict[str, Any]] = None, **kwargs: Any) None¶

Run when tool starts running.

Parameters
  • serialized (Dict[str, Any]) –

  • input_str (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

  • metadata (Optional[Dict[str, Any]]) –

  • inputs (Optional[Dict[str, Any]]) –

  • kwargs (Any) –

Return type

None