langchain_community.callbacks.labelstudio_callback
.LabelStudioCallbackHandler¶
- class langchain_community.callbacks.labelstudio_callback.LabelStudioCallbackHandler(api_key: Optional[str] = None, url: Optional[str] = None, project_id: Optional[int] = None, project_name: str = 'LangChain-%Y-%m-%d', project_config: Optional[str] = None, mode: Union[str, LabelStudioMode] = LabelStudioMode.PROMPT)[source]¶
Label Studio callback handler. Provides the ability to send predictions to Label Studio for human evaluation, feedback and annotation.
- Parameters
api_key – Label Studio API key
url – Label Studio URL
project_id – Label Studio project ID
project_name – Label Studio project name
project_config – Label Studio project config (XML)
mode – Label Studio mode (“prompt” or “chat”)
Examples
>>> from langchain_community.llms import OpenAI >>> from langchain_community.callbacks import LabelStudioCallbackHandler >>> handler = LabelStudioCallbackHandler( ... api_key='<your_key_here>', ... url='http://localhost:8080', ... project_name='LangChain-%Y-%m-%d', ... mode='prompt' ... ) >>> llm = OpenAI(callbacks=[handler]) >>> llm.predict('Tell me a story about a dog.')
Attributes
DEFAULT_PROJECT_NAME
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__
([api_key, url, project_id, ...])add_prompts_generations
(run_id, generations)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)Run when chain ends running.
on_chain_error
(error, **kwargs)Do nothing when LLM chain outputs an error.
on_chain_start
(serialized, inputs, **kwargs)Run when chain starts running.
on_chat_model_start
(serialized, messages, *, ...)Save the prompts in memory when an LLM starts.
on_llm_end
(response, **kwargs)Create a new Label Studio task for each prompt and generation.
on_llm_error
(error, **kwargs)Do nothing when LLM outputs an error.
on_llm_new_token
(token, **kwargs)Do nothing when a new token is generated.
on_llm_start
(serialized, prompts, **kwargs)Save the prompts in memory when an 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)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.
- __init__(api_key: Optional[str] = None, url: Optional[str] = None, project_id: Optional[int] = None, project_name: str = 'LangChain-%Y-%m-%d', project_config: Optional[str] = None, mode: Union[str, LabelStudioMode] = LabelStudioMode.PROMPT)[source]¶
- add_prompts_generations(run_id: str, generations: List[List[Generation]]) None [source]¶
- on_agent_action(action: AgentAction, **kwargs: Any) Any [source]¶
Do nothing when agent takes a specific action.
- on_agent_finish(finish: AgentFinish, **kwargs: Any) None [source]¶
Do nothing
- on_chain_error(error: BaseException, **kwargs: Any) None [source]¶
Do nothing when LLM chain outputs an error.
- on_chain_start(serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any) None [source]¶
Run when chain starts running.
- 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 [source]¶
Save the prompts in memory when an LLM starts.
- on_llm_end(response: LLMResult, **kwargs: Any) None [source]¶
Create a new Label Studio task for each prompt and generation.
- on_llm_error(error: BaseException, **kwargs: Any) None [source]¶
Do nothing when LLM outputs an error.
- on_llm_new_token(token: str, **kwargs: Any) None [source]¶
Do nothing when a new token is generated.
- on_llm_start(serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) None [source]¶
Save the prompts in memory when an LLM starts.
- on_retriever_end(documents: Sequence[Document], *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run when Retriever ends running.
- on_retriever_error(error: BaseException, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
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, **kwargs: Any) Any ¶
Run when Retriever starts running.
- on_retry(retry_state: RetryCallState, *, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any) Any ¶
Run on a retry event.
- on_tool_end(output: str, observation_prefix: Optional[str] = None, llm_prefix: Optional[str] = None, **kwargs: Any) None [source]¶
Do nothing when tool ends.