langchain_experimental.plan_and_execute.planners.base.LLMPlanner¶

class langchain_experimental.plan_and_execute.planners.base.LLMPlanner[source]¶

Bases: BasePlanner

LLM planner.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param llm_chain: LLMChain [Required]¶

The LLM chain to use.

param output_parser: PlanOutputParser [Required]¶

The output parser to use.

param stop: Optional[List] = None¶

The stop list to use.

async aplan(inputs: dict, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) → Plan[source]¶

Given input, asynchronously decide what to do.

Parameters
Return type

Plan

plan(inputs: dict, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) → Plan[source]¶

Given input, decide what to do.

Parameters
Return type

Plan