langchain_core.tracers.evaluation.EvaluatorCallbackHandler

class langchain_core.tracers.evaluation.EvaluatorCallbackHandler(evaluators: Sequence[RunEvaluator], client: Optional[Client] = None, example_id: Optional[Union[str, UUID]] = None, skip_unfinished: bool = True, project_name: Optional[str] = 'evaluators', max_concurrency: Optional[int] = None, **kwargs: Any)

A tracer that runs a run evaluator whenever a run is persisted.

Parameters

• evaluators (Sequence[RunEvaluator]) – The run evaluators to apply to all top level runs.

• client (LangSmith Client, optional) – The LangSmith client instance to use for evaluating the runs. If not specified, a new instance will be created.

• example_id (Union[UUID, str], optional) – The example ID to be associated with the runs.

• project_name (str, optional) – The LangSmith project name to be organize eval chain runs under.

example_id

The example ID associated with the runs.

Type

Union[UUID, None]

client

The LangSmith client instance used for evaluating the runs.

Type

Client

evaluators

The sequence of run evaluators to be executed.

Type

Sequence[RunEvaluator]

executor

The thread pool executor used for running the evaluators.

Type

ThreadPoolExecutor

futures

The set of futures representing the running evaluators.

Type

Set[Future]

skip_unfinished

Whether to skip runs that are not finished or raised an error.

Type

bool

project_name

The LangSmith project name to be organize eval chain runs under.

Type

Optional[str]

Initialize the tracer.

Parameters

• _schema_format –

  Primarily changes how the inputs and outputs are handled. For internal use only. This API will change. - ‘original’ is the format used by all current tracers.

  This format is slightly inconsistent with respect to inputs and outputs.

  • ’streaming_events’ is used for supporting streaming events,

    for internal usage. It will likely change in the future, or be deprecated entirely in favor of a dedicated async tracer for streaming events.

• kwargs – Additional keyword arguments that will be passed to the super class.

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.
name
raise_error
run_inline

Methods

__init__(evaluators[, client, example_id, ...])	Initialize the tracer.
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[, inputs])	End a trace for a chain run.
on_chain_error(error, *[, inputs])	Handle an error for a chain run.
on_chain_start(serialized, inputs, *, run_id)	Start a trace for a chain run.
on_chat_model_start(serialized, messages, *, ...)	Start a trace for an LLM run.
on_llm_end(response, *, run_id, **kwargs)	End a trace for an LLM run.
on_llm_error(error, *, run_id, **kwargs)	Handle an error for an LLM run.
on_llm_new_token(token, *[, chunk, ...])	Run on new LLM token.
on_llm_start(serialized, prompts, *, run_id)	Start a trace for an LLM run.
on_retriever_end(documents, *, run_id, **kwargs)	Run when Retriever ends running.
on_retriever_error(error, *, run_id, **kwargs)	Run when Retriever errors.
on_retriever_start(serialized, query, *, run_id)	Run when Retriever starts running.
on_retry(retry_state, *, run_id, **kwargs)	Run on a retry event.
on_text(text, *, run_id[, parent_run_id])	Run on arbitrary text.
on_tool_end(output, *, run_id, **kwargs)	End a trace for a tool run.
on_tool_error(error, *, run_id, **kwargs)	Handle an error for a tool run.
on_tool_start(serialized, input_str, *, run_id)	Start a trace for a tool run.
wait_for_futures()	Wait for all futures to complete.

__init__(evaluators: Sequence[RunEvaluator], client: Optional[Client] = None, example_id: Optional[Union[str, UUID]] = None, skip_unfinished: bool = True, project_name: Optional[str] = 'evaluators', max_concurrency: Optional[int] = None, **kwargs: Any) → None

Initialize the tracer.

Parameters

• _schema_format –

  Primarily changes how the inputs and outputs are handled. For internal use only. This API will change. - ‘original’ is the format used by all current tracers.

  This format is slightly inconsistent with respect to inputs and outputs.

  • ’streaming_events’ is used for supporting streaming events,

    for internal usage. It will likely change in the future, or be deprecated entirely in favor of a dedicated async tracer for streaming events.

• kwargs – Additional keyword arguments that will be passed to the super class.

on_agent_action(action: AgentAction, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any

Run on agent action.

on_agent_finish(finish: AgentFinish, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any

Run on agent end.

on_chain_end(outputs: Dict[str, Any], *, run_id: UUID, inputs: Optional[Dict[str, Any]] = None, **kwargs: Any) → Run

End a trace for a chain run.

on_chain_error(error: BaseException, *, inputs: Optional[Dict[str, Any]] = None, run_id: UUID, **kwargs: Any) → Run

Handle an error for a chain run.

on_chain_start(serialized: Dict[str, Any], inputs: Dict[str, Any], *, run_id: UUID, tags: Optional[List[str]] = None, parent_run_id: Optional[UUID] = None, metadata: Optional[Dict[str, Any]] = None, run_type: Optional[str] = None, name: Optional[str] = None, **kwargs: Any) → Run

Start a trace for a chain run.

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

Start a trace for an LLM run.

on_llm_end(response: LLMResult, *, run_id: UUID, **kwargs: Any) → Run

End a trace for an LLM run.

on_llm_error(error: BaseException, *, run_id: UUID, **kwargs: Any) → Run

Handle an error for an LLM run.

on_llm_new_token(token: str, *, chunk: Optional[Union[GenerationChunk, ChatGenerationChunk]] = None, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Run

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

on_llm_start(serialized: Dict[str, Any], prompts: List[str], *, run_id: UUID, tags: Optional[List[str]] = None, parent_run_id: Optional[UUID] = None, metadata: Optional[Dict[str, Any]] = None, name: Optional[str] = None, **kwargs: Any) → Run

Start a trace for an LLM run.

on_retriever_end(documents: Sequence[Document], *, run_id: UUID, **kwargs: Any) → Run

Run when Retriever ends running.

on_retriever_error(error: BaseException, *, run_id: UUID, **kwargs: Any) → Run

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, name: Optional[str] = None, **kwargs: Any) → Run

Run when Retriever starts running.

on_retry(retry_state: RetryCallState, *, run_id: UUID, **kwargs: Any) → Run

Run on a retry event.

on_text(text: str, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any

Run on arbitrary text.

on_tool_end(output: str, *, run_id: UUID, **kwargs: Any) → Run

End a trace for a tool run.

on_tool_error(error: BaseException, *, run_id: UUID, **kwargs: Any) → Run

Handle an error for a tool run.

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

Start a trace for a tool run.

wait_for_futures() → None

Wait for all futures to complete.