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)[source]¶

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.

  • skip_unfinished (bool) –

  • max_concurrency (Optional[int]) –

  • kwargs (Any) –

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 (Any) – Additional keyword arguments that will be passed to the super class.

  • evaluators (Sequence[langsmith.RunEvaluator]) –

  • client (Optional[langsmith.Client]) –

  • example_id (Optional[Union[UUID, str]]) –

  • skip_unfinished (bool) –

  • project_name (Optional[str]) –

  • max_concurrency (Optional[int]) –

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[source]¶

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 (Any) – Additional keyword arguments that will be passed to the super class.

  • evaluators (Sequence[RunEvaluator]) –

  • client (Optional[Client]) –

  • example_id (Optional[Union[str, UUID]]) –

  • skip_unfinished (bool) –

  • project_name (Optional[str]) –

  • max_concurrency (Optional[int]) –

Return type

None

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

Run on agent action.

Parameters

  • action (AgentAction) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

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

Run on agent end.

Parameters

  • finish (AgentFinish) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

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.

Parameters

  • outputs (Dict[str, Any]) –

  • run_id (UUID) –

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

  • kwargs (Any) –

Return type

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.

Parameters

  • error (BaseException) –

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

  • run_id (UUID) –

  • kwargs (Any) –

Return type

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.

Parameters

  • serialized (Dict[str, Any]) –

  • inputs (Dict[str, Any]) –

  • run_id (UUID) –

  • tags (Optional[List[str]]) –

  • parent_run_id (Optional[UUID]) –

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

  • run_type (Optional[str]) –

  • name (Optional[str]) –

  • kwargs (Any) –

Return type

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.

Parameters

  • serialized (Dict[str, Any]) –

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

  • run_id (UUID) –

  • tags (Optional[List[str]]) –

  • parent_run_id (Optional[UUID]) –

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

  • name (Optional[str]) –

  • kwargs (Any) –

Return type

Run

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

End a trace for an LLM run.

Parameters

  • response (LLMResult) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

Run

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

Handle an error for an LLM run.

Parameters

  • error (BaseException) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

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.

Parameters

  • token (str) –

  • chunk (Optional[Union[GenerationChunk, ChatGenerationChunk]]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Run

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.

Parameters

  • serialized (Dict[str, Any]) –

  • prompts (List[str]) –

  • run_id (UUID) –

  • tags (Optional[List[str]]) –

  • parent_run_id (Optional[UUID]) –

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

  • name (Optional[str]) –

  • kwargs (Any) –

Return type

Run

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

Run when Retriever ends running.

Parameters

  • documents (Sequence[Document]) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

Run

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

Run when Retriever errors.

Parameters

  • error (BaseException) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

Run

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.

Parameters

  • serialized (Dict[str, Any]) –

  • query (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

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

  • name (Optional[str]) –

  • kwargs (Any) –

Return type

Run

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

Run on a retry event.

Parameters

  • retry_state (RetryCallState) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

Run

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

Run on arbitrary text.

Parameters

  • text (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

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

End a trace for a tool run.

Parameters

  • output (Any) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

Run

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

Handle an error for a tool run.

Parameters

  • error (BaseException) –

  • run_id (UUID) –

  • kwargs (Any) –

Return type

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.

Parameters

  • serialized (Dict[str, Any]) –

  • input_str (str) –

  • run_id (UUID) –

  • tags (Optional[List[str]]) –

  • parent_run_id (Optional[UUID]) –

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

  • name (Optional[str]) –

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

  • kwargs (Any) –

Return type

Run

wait_for_futures() → None[source]¶

Wait for all futures to complete.

Return type

None