langchain_community.callbacks.arthur_callback.ArthurCallbackHandler¶

class langchain_community.callbacks.arthur_callback.ArthurCallbackHandler(arthur_model: ArthurModel)[source]¶

Callback Handler that logs to Arthur platform.

Arthur helps enterprise teams optimize model operations and performance at scale. The Arthur API tracks model performance, explainability, and fairness across tabular, NLP, and CV models. Our API is model- and platform-agnostic, and continuously scales with complex and dynamic enterprise needs. To learn more about Arthur, visit our website at https://www.arthur.ai/ or read the Arthur docs at https://docs.arthur.ai/

Initialize callback handler.

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__(arthur_model)

Initialize callback handler.

from_credentials(model_id[, arthur_url, ...])

Initialize callback handler from Arthur credentials.

on_agent_action(action, **kwargs)

Do nothing when agent takes a specific action.

on_agent_finish(finish, **kwargs)

Do nothing

on_chain_end(outputs, **kwargs)

On chain end, do nothing.

on_chain_error(error, **kwargs)

Do nothing when LLM chain outputs an error.

on_chain_start(serialized, inputs, **kwargs)

On chain start, do nothing.

on_chat_model_start(serialized, messages, *, ...)

Run when a chat model starts running.

on_llm_end(response, **kwargs)

On LLM end, send data to Arthur.

on_llm_error(error, **kwargs)

Do nothing when LLM outputs an error.

on_llm_new_token(token, **kwargs)

On new token, pass.

on_llm_start(serialized, prompts, **kwargs)

On LLM start, save the input prompts

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)

Do nothing

on_tool_end(output[, observation_prefix, ...])

Do nothing when tool ends.

on_tool_error(error, **kwargs)

Do nothing when tool outputs an error.

on_tool_start(serialized, input_str, **kwargs)

Do nothing when tool starts.
Parameters

arthur_model (ArthurModel) –

__init__(arthur_model: ArthurModel) → None[source]¶

Initialize callback handler.

Parameters

arthur_model (ArthurModel) –

Return type

None

classmethod from_credentials(model_id: str, arthur_url: Optional[str] = 'https://app.arthur.ai', arthur_login: Optional[str] = None, arthur_password: Optional[str] = None) → ArthurCallbackHandler[source]¶

Initialize callback handler from Arthur credentials.

Parameters

  • model_id (str) – The ID of the arthur model to log to.

  • arthur_url (str, optional) – The URL of the Arthur instance to log to. Defaults to “https://app.arthur.ai”.

  • arthur_login (str, optional) – The login to use to connect to Arthur. Defaults to None.

  • arthur_password (str, optional) – The password to use to connect to Arthur. Defaults to None.

Returns

The initialized callback handler.

Return type

ArthurCallbackHandler

on_agent_action(action: AgentAction, **kwargs: Any) → Any[source]¶

Do nothing when agent takes a specific action.

Parameters
Return type

Any

on_agent_finish(finish: AgentFinish, **kwargs: Any) → None[source]¶

Do nothing

Parameters
Return type

None

on_chain_end(outputs: Dict[str, Any], **kwargs: Any) → None[source]¶

On chain end, do nothing.

Parameters

  • outputs (Dict[str, Any]) –

  • kwargs (Any) –

Return type

None

on_chain_error(error: BaseException, **kwargs: Any) → None[source]¶

Do nothing when LLM chain outputs an error.

Parameters

  • error (BaseException) –

  • kwargs (Any) –

Return type

None

on_chain_start(serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any) → None[source]¶

On chain start, do nothing.

Parameters

  • serialized (Dict[str, Any]) –

  • inputs (Dict[str, Any]) –

  • kwargs (Any) –

Return type

None

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.

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]) –

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

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

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

  • kwargs (Any) –

Return type

Any

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

On LLM end, send data to Arthur.

Parameters

  • response (LLMResult) –

  • kwargs (Any) –

Return type

None

on_llm_error(error: BaseException, **kwargs: Any) → None[source]¶

Do nothing when LLM outputs an error.

Parameters

  • error (BaseException) –

  • kwargs (Any) –

Return type

None

on_llm_new_token(token: str, **kwargs: Any) → None[source]¶

On new token, pass.

Parameters

  • token (str) –

  • kwargs (Any) –

Return type

None

on_llm_start(serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) → None[source]¶

On LLM start, save the input prompts

Parameters

  • serialized (Dict[str, Any]) –

  • prompts (List[str]) –

  • kwargs (Any) –

Return type

None

on_retriever_end(documents: Sequence[Document], *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any¶

Run when Retriever ends running.

Parameters

  • documents (Sequence[Document]) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any¶

Run when Retriever errors.

Parameters

  • error (BaseException) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

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.

Parameters

  • serialized (Dict[str, Any]) –

  • query (str) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • tags (Optional[List[str]]) –

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

  • kwargs (Any) –

Return type

Any

on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) → Any¶

Run on a retry event.

Parameters

  • retry_state (RetryCallState) –

  • run_id (UUID) –

  • parent_run_id (Optional[UUID]) –

  • kwargs (Any) –

Return type

Any

on_text(text: str, **kwargs: Any) → None[source]¶

Do nothing

Parameters

  • text (str) –

  • kwargs (Any) –

Return type

None

on_tool_end(output: Any, observation_prefix: Optional[str] = None, llm_prefix: Optional[str] = None, **kwargs: Any) → None[source]¶

Do nothing when tool ends.

Parameters

  • output (Any) –

  • observation_prefix (Optional[str]) –

  • llm_prefix (Optional[str]) –

  • kwargs (Any) –

Return type

None

on_tool_error(error: BaseException, **kwargs: Any) → None[source]¶

Do nothing when tool outputs an error.

Parameters

  • error (BaseException) –

  • kwargs (Any) –

Return type

None

on_tool_start(serialized: Dict[str, Any], input_str: str, **kwargs: Any) → None[source]¶

Do nothing when tool starts.

Parameters

  • serialized (Dict[str, Any]) –

  • input_str (str) –

  • kwargs (Any) –

Return type

None

Examples using ArthurCallbackHandler¶