`langchain_community.callbacks.wandb_callback`.WandbCallbackHandler¶

class langchain_community.callbacks.wandb_callback.WandbCallbackHandler(job_type: Optional[str] = None, project: Optional[str] = 'langchain_callback_demo', entity: Optional[str] = None, tags: Optional[Sequence] = None, group: Optional[str] = None, name: Optional[str] = None, notes: Optional[str] = None, visualize: bool = False, complexity_metrics: bool = False, stream_logs: bool = False)[source]¶

Callback Handler that logs to Weights and Biases.

Parameters

job_type (str) – The type of job.
project (str) – The project to log to.
entity (str) – The entity to log to.
tags (list) – The tags to log.
group (str) – The group to log to.
name (str) – The name of the run.
notes (str) – The notes to log.
visualize (bool) – Whether to visualize the run.
complexity_metrics (bool) – Whether to log complexity metrics.
stream_logs (bool) – Whether to stream callback actions to W&B

This handler will utilize the associated callback method called 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 using the run.log() method to Weights and Biases.

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_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__`([job_type, project, entity, tags, ...])	Initialize callback handler.
`flush_tracker`([langchain_asset, reset, ...])	Flush the tracker and reset 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_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 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__(job_type: Optional[str] = None, project: Optional[str] = 'langchain_callback_demo', entity: Optional[str] = None, tags: Optional[Sequence] = None, group: Optional[str] = None, name: Optional[str] = None, notes: Optional[str] = None, visualize: bool = False, complexity_metrics: bool = False, stream_logs: bool = False) → None[source]¶

Initialize callback handler.

Parameters

job_type (Optional[str]) –
project (Optional[str]) –
entity (Optional[str]) –
tags (Optional[Sequence]) –
group (Optional[str]) –
name (Optional[str]) –
notes (Optional[str]) –
visualize (bool) –
complexity_metrics (bool) –
stream_logs (bool) –

Return type

None

flush_tracker(langchain_asset: Any = None, reset: bool = True, finish: bool = False, job_type: Optional[str] = None, project: Optional[str] = None, entity: Optional[str] = None, tags: Optional[Sequence] = None, group: Optional[str] = None, name: Optional[str] = None, notes: Optional[str] = None, visualize: Optional[bool] = None, complexity_metrics: Optional[bool] = None) → None[source]¶

Flush the tracker and reset the session.

Parameters

langchain_asset (Any) – The langchain asset to save.
reset (bool) – Whether to reset the session.
finish (bool) – Whether to finish the run.
job_type (Optional[str]) – The job type.
project (Optional[str]) – The project.
entity (Optional[str]) – The entity.
tags (Optional[Sequence]) – The tags.
group (Optional[str]) – The group.
name (Optional[str]) – The name.
notes (Optional[str]) – The notes.
visualize (Optional[bool]) – Whether to visualize.
complexity_metrics (Optional[bool]) – Whether to compute complexity metrics.
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[source]¶

Run on agent action.

Parameters

action (AgentAction) –
kwargs (Any) –

Return type

Any

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

Run when agent ends running.

Parameters

finish (AgentFinish) –
kwargs (Any) –

Return type

None

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

Run when chain ends running.

Parameters

outputs (Dict[str, Any]) –
kwargs (Any) –

Return type

None

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

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[source]¶

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: 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]¶

Run when LLM ends running.

Parameters

response (LLMResult) –
kwargs (Any) –

Return type

None

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

Run when LLM errors.

Parameters

error (BaseException) –
kwargs (Any) –

Return type

None

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

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[source]¶

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: 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]¶

Run when agent is ending.

Parameters

text (str) –
kwargs (Any) –

Return type

None

on_tool_end(output: Any, **kwargs: Any) → None[source]¶

Run when tool ends running.

Parameters

output (Any) –
kwargs (Any) –

Return type

None

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

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[source]¶

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 WandbCallbackHandler¶

Weights & Biases

langchain_community.callbacks.wandb_callback.WandbCallbackHandler¶

Examples using WandbCallbackHandler¶

`langchain_community.callbacks.wandb_callback`.WandbCallbackHandler¶