AsyncFinalIteratorCallbackHandler#

class langchain.callbacks.streaming_aiter_final_only.AsyncFinalIteratorCallbackHandler(*, answer_prefix_tokens: List[str] | None = 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_custom_event`	Ignore custom event.
`ignore_llm`	Whether to ignore LLM callbacks.
`ignore_retriever`	Whether to ignore retriever callbacks.
`ignore_retry`	Whether to ignore retry callbacks.
`raise_error`	Whether to raise an error if an exception occurs.
`run_inline`	Whether to run the callback inline.
`queue`	A multi-producer, multi-consumer queue.

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 the agent end.
`on_chain_end`(outputs, *, run_id[, ...])	Run when a chain ends running.
`on_chain_error`(error, *, run_id[, ...])	Run when chain errors.
`on_chain_start`(serialized, inputs, *, run_id)	Run when a chain starts running.
`on_chat_model_start`(serialized, messages, *, ...)	Run when a chat model starts running.
`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, **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 the retriever end.
`on_retriever_error`(error, *, run_id[, ...])	Run on retriever error.
`on_retriever_start`(serialized, query, *, run_id)	Run on the 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 an arbitrary text.
`on_tool_end`(output, *, run_id[, ...])	Run when the tool ends running.
`on_tool_error`(error, *, run_id[, ...])	Run when tool errors.
`on_tool_start`(serialized, input_str, *, run_id)	Run when the tool starts running.

__init__(*, answer_prefix_tokens: List[str] | None = None, strip_tokens: bool = True, stream_prefix: bool = False) → None[source]#

Instantiate AsyncFinalIteratorCallbackHandler.

Parameters:

answer_prefix_tokens (List[str] | None) – 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: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run on agent action.

Parameters:

action (AgentAction) – The agent action.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_agent_finish(finish: AgentFinish, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run on the agent end.

Parameters:

finish (AgentFinish) – The agent finish.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_chain_end(outputs: dict[str, Any], *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run when a chain ends running.

Parameters:

outputs (Dict[str, Any]) – The outputs of the chain.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_chain_error(error: BaseException, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run when chain errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_chain_start(serialized: dict[str, Any], inputs: dict[str, Any], *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, metadata: dict[str, Any] | None = None, **kwargs: Any) → None#

Run when a chain starts running.

Parameters:

serialized (Dict[str, Any]) – The serialized chain.
inputs (Dict[str, Any]) – The inputs.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
metadata (Optional[Dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_chat_model_start(serialized: dict[str, Any], messages: list[list[BaseMessage]], *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, metadata: dict[str, Any] | None = 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]) – The serialized chat model.
messages (List[List[BaseMessage]]) – The messages.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
metadata (Optional[Dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

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

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:

None

Added in version 0.2.15.

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

Run when LLM ends running.

Parameters:

response (LLMResult) – The response which was generated.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

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

Run when LLM errors.

Parameters:

error (BaseException) – The error that occurred.
run_id – The run ID. This is the ID of the current run.
parent_run_id – The parent run ID. This is the ID of the parent run.
tags – The tags.
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) – The new token.
chunk (GenerationChunk | ChatGenerationChunk) – The new generated chunk, containing content and other information.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

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]) – The serialized LLM.
prompts (List[str]) – The prompts.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
metadata (Optional[Dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_retriever_end(documents: Sequence[Document], *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run on the retriever end.

Parameters:

documents (Sequence[Document]) – The documents retrieved.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run on retriever error.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_retriever_start(serialized: dict[str, Any], query: str, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, metadata: dict[str, Any] | None = None, **kwargs: Any) → None#

Run on the retriever start.

Parameters:

serialized (Dict[str, Any]) – The serialized retriever.
query (str) – The query.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
metadata (Optional[Dict[str, Any]]) – The metadata.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: UUID | None = None, **kwargs: Any) → Any#

Run on a retry event.

Parameters:

retry_state (RetryCallState) – The retry state.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
kwargs (Any) – Additional keyword arguments.

Return type:

Any

async on_text(text: str, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run on an arbitrary text.

Parameters:

text (str) – The text.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_tool_end(output: Any, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run when the tool ends running.

Parameters:

output (Any) – The output of the tool.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_tool_error(error: BaseException, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, **kwargs: Any) → None#

Run when tool errors.

Parameters:

error (BaseException) – The error that occurred.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
kwargs (Any) – Additional keyword arguments.

Return type:

None

async on_tool_start(serialized: dict[str, Any], input_str: str, *, run_id: UUID, parent_run_id: UUID | None = None, tags: list[str] | None = None, metadata: dict[str, Any] | None = None, inputs: dict[str, Any] | None = None, **kwargs: Any) → None#

Run when the tool starts running.

Parameters:

serialized (Dict[str, Any]) – The serialized tool.
input_str (str) – The input string.
run_id (UUID) – The run ID. This is the ID of the current run.
parent_run_id (UUID) – The parent run ID. This is the ID of the parent run.
tags (Optional[List[str]]) – The tags.
metadata (Optional[Dict[str, Any]]) – The metadata.
inputs (Optional[Dict[str, Any]]) – The inputs.
kwargs (Any) – Additional keyword arguments.

Return type:

None