langchain.callbacks.streaming_stdout_final_only
.FinalStreamingStdOutCallbackHandler¶
- class langchain.callbacks.streaming_stdout_final_only.FinalStreamingStdOutCallbackHandler(*, answer_prefix_tokens: Optional[List[str]] = None, strip_tokens: bool = True, stream_prefix: bool = False)[source]¶
Callback handler for streaming in agents. Only works with agents using LLMs that support streaming.
Only the final output of the agent will be streamed.
Instantiate FinalStreamingStdOutCallbackHandler.
- 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
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 FinalStreamingStdOutCallbackHandler.
append_to_last_tokens
(token)on_agent_action
(action, **kwargs)Run on agent action.
on_agent_finish
(finish, **kwargs)Run on agent end.
on_chain_end
(outputs, **kwargs)Run when chain ends running.
on_chain_error
(error, **kwargs)Run when chain errors.
on_chain_start
(serialized, inputs, **kwargs)Run when chain starts running.
on_chat_model_start
(serialized, messages, ...)Run when LLM 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 when Retriever ends running.
on_retriever_error
(error, *, run_id[, ...])Run when Retriever errors.
on_retriever_start
(serialized, query, *, run_id)Run when Retriever starts running.
on_retry
(retry_state, *, run_id[, parent_run_id])Run on a retry event.
on_text
(text, **kwargs)Run on arbitrary text.
on_tool_end
(output, **kwargs)Run when tool ends running.
on_tool_error
(error, **kwargs)Run when tool errors.
on_tool_start
(serialized, input_str, **kwargs)Run when tool starts running.
- __init__(*, answer_prefix_tokens: Optional[List[str]] = None, strip_tokens: bool = True, stream_prefix: bool = False) None [source]¶
Instantiate FinalStreamingStdOutCallbackHandler.
- 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?
- on_agent_action(action: AgentAction, **kwargs: Any) Any ¶
Run on agent action.
- on_agent_finish(finish: AgentFinish, **kwargs: Any) None ¶
Run on agent end.
- on_chain_end(outputs: Dict[str, Any], **kwargs: Any) None ¶
Run when chain ends running.
- on_chain_error(error: BaseException, **kwargs: Any) None ¶
Run when chain errors.
- on_chain_start(serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any) None ¶
Run when chain starts running.
- on_chat_model_start(serialized: Dict[str, Any], messages: List[List[BaseMessage]], **kwargs: Any) None ¶
Run when LLM starts running.
- on_llm_error(error: BaseException, **kwargs: Any) None ¶
Run when LLM errors.
- on_llm_new_token(token: str, **kwargs: Any) None [source]¶
Run on new LLM token. Only available when streaming is enabled.
- on_llm_start(serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) None [source]¶
Run when LLM starts running.
- on_retriever_end(documents: Sequence[Document], *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run when Retriever ends running.
- on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run when Retriever errors.
- 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) Any ¶
Run when Retriever starts running.
- on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run on a retry event.
- on_text(text: str, **kwargs: Any) None ¶
Run on arbitrary text.
- on_tool_end(output: str, **kwargs: Any) None ¶
Run when tool ends running.
- on_tool_error(error: BaseException, **kwargs: Any) None ¶
Run when tool errors.
- on_tool_start(serialized: Dict[str, Any], input_str: str, **kwargs: Any) None ¶
Run when tool starts running.