ClearMLCallbackHandler

class langchain_community.callbacks.clearml_callback.ClearMLCallbackHandler(task_type: str | None = 'inference', project_name: str | None = 'langchain_callback_demo', tags: Sequence | None = None, task_name: str | None = None, visualize: bool = False, complexity_metrics: bool = False, stream_logs: bool = False)

Callback Handler that logs to ClearML.

Parameters:

• job_type (str) – The type of clearml task such as “inference”, “testing” or “qc”

• project_name (str) – The clearml project name

• tags (list) – Tags to add to the task

• task_name (str) – Name of the clearml task

• visualize (bool) – Whether to visualize the run.

• complexity_metrics (bool) – Whether to log complexity metrics

• stream_logs (bool) – Whether to stream callback actions to ClearML

• task_type (Optional[str]) –

This handler will utilize the associated callback method and formats the input of each callback function with metadata regarding the state of LLM run, and adds the response to the list of records for both the {method}_records and action. It then logs the response to the ClearML console.

Initialize callback handler.

Attributes

always_verbose	Whether to call verbose callbacks even if verbose is False.
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.

Methods

__init__([task_type, project_name, tags, ...])	Initialize callback handler.
analyze_text(text)	Analyze text using textstat and spacy.
flush_tracker([name, langchain_asset, finish])	Flush the tracker and setup the session.
get_custom_callback_meta()
on_agent_action(action, **kwargs)	Run on agent action.
on_agent_finish(finish, **kwargs)	Run when agent ends running.
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 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 when LLM generates a new token.
on_llm_start(serialized, prompts, **kwargs)	Run when LLM starts.
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 the Retriever starts running.
on_retry(retry_state, *, run_id[, parent_run_id])	Run on a retry event.
on_text(text, **kwargs)	Run when agent is ending.
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.
reset_callback_meta()	Reset the callback metadata.

__init__(task_type: str | None = 'inference', project_name: str | None = 'langchain_callback_demo', tags: Sequence | None = None, task_name: str | None = None, visualize: bool = False, complexity_metrics: bool = False, stream_logs: bool = False) → None

Initialize callback handler.

Parameters:

• task_type (str | None) –

• project_name (str | None) –

• tags (Sequence | None) –

• task_name (str | None) –

• visualize (bool) –

• complexity_metrics (bool) –

• stream_logs (bool) –

Return type:

None

analyze_text(text: str) → dict

Analyze text using textstat and spacy.

Parameters:

text (str) – The text to analyze.

Returns:

A dictionary containing the complexity metrics.

Return type:

(dict)

flush_tracker(name: str | None = None, langchain_asset: Any = None, finish: bool = False) → None

Flush the tracker and setup the session.

Everything after this will be a new table.

Parameters:

• name (str | None) – Name of the performed session so far so it is identifiable

• langchain_asset (Any) – The langchain asset to save.

• finish (bool) – Whether to finish the run.

• Returns – None

Return type:

None

get_custom_callback_meta() → Dict[str, Any]

Return type:

Dict[str, Any]

on_agent_action(action: AgentAction, **kwargs: Any) → Any

Run on agent action.

Parameters:

• action (AgentAction) –

• kwargs (Any) –

Return type:

Any

on_agent_finish(finish: AgentFinish, **kwargs: Any) → None

Run when agent ends running.

Parameters:

• finish (AgentFinish) –

• kwargs (Any) –

Return type:

None

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

Run when chain ends running.

Parameters:

• outputs (Dict[str, Any]) –

• kwargs (Any) –

Return type:

None

on_chain_error(error: BaseException, **kwargs: Any) → None

Run when chain errors.

Parameters:

• error (BaseException) –

• kwargs (Any) –

Return type:

None

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

Run when chain starts running.

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: 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

on_custom_event(name: str, data: Any, *, run_id: UUID, tags: List[str] | None = None, metadata: Dict[str, Any] | None = None, **kwargs: Any) → Any

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:

Any

New in version 0.2.15.

on_llm_end(response: LLMResult, **kwargs: Any) → None

Run when LLM ends running.

Parameters:

• response (LLMResult) –

• kwargs (Any) –

Return type:

None

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

Run when LLM errors.

Parameters:

• error (BaseException) –

• kwargs (Any) –

Return type:

None

on_llm_new_token(token: str, **kwargs: Any) → None

Run when LLM generates a new token.

Parameters:

• token (str) –

• kwargs (Any) –

Return type:

None

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

Run when LLM starts.

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: UUID | None = None, **kwargs: Any) → Any

Run when Retriever ends running.

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.

• kwargs (Any) – Additional keyword arguments.

Return type:

Any

on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: UUID | None = None, **kwargs: Any) → Any

Run when Retriever 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.

• kwargs (Any) – Additional keyword arguments.

Return type:

Any

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) → Any

Run when the Retriever starts running.

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:

Any

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

on_text(text: str, **kwargs: Any) → None

Run when agent is ending.

Parameters:

• text (str) –

• kwargs (Any) –

Return type:

None

on_tool_end(output: Any, **kwargs: Any) → None

Run when tool ends running.

Parameters:

• output (Any) –

• kwargs (Any) –

Return type:

None

on_tool_error(error: BaseException, **kwargs: Any) → None

Run when tool errors.

Parameters:

• error (BaseException) –

• kwargs (Any) –

Return type:

None

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

Run when tool starts running.

Parameters:

• serialized (Dict[str, Any]) –

• input_str (str) –

• kwargs (Any) –

Return type:

None

reset_callback_meta() → None

Reset the callback metadata.

Return type:

None

Examples using ClearMLCallbackHandler

• ClearML