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 – Token sequence that prefixes the answer. Default is [“Final”, “Answer”, “:”]
strip_tokens – Ignore white spaces and new lines when comparing answer_prefix_tokens to last tokens? (to determine if answer has been reached)
stream_prefix – 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)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. :param error: The error that occurred. :type error: BaseException :param kwargs: Additional keyword arguments. - response (LLMResult): The response which was generated before the error occurred. :type kwargs: Any.
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 – Token sequence that prefixes the answer. Default is [“Final”, “Answer”, “:”]
strip_tokens – Ignore white spaces and new lines when comparing answer_prefix_tokens to last tokens? (to determine if answer has been reached)
stream_prefix – Should answer prefix itself also be streamed?
- async aiter() AsyncIterator[str] ¶
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- async on_llm_error(error: BaseException, **kwargs: Any) None ¶
Run when LLM errors. :param error: The error that occurred. :type error: BaseException :param kwargs: Additional keyword arguments.
- response (LLMResult): The response which was generated before
the error occurred.
- async on_llm_new_token(token: str, **kwargs: Any) None [source]¶
Run on new LLM token. Only available when streaming is enabled.
- async on_llm_start(serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) None [source]¶
Run when LLM starts running.
- 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.
- 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.
- 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.
- async on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run on a retry event.
- 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.
- async on_tool_end(output: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, tags: Optional[List[str]] = None, **kwargs: Any) None ¶
Run when tool ends running.
- 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.
- 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, **kwargs: Any) None ¶
Run when tool starts running.