LLMPlanner

class langchain_experimental.plan_and_execute.planners.base.LLMPlanner

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: List | None = None

The stop list to use.

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

Given input, asynchronously decide what to do.

Parameters:

• inputs (dict) –

• callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) –

• kwargs (Any) –

Return type:

Plan

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

Given input, decide what to do.

Parameters:

• inputs (dict) –

• callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) –

• kwargs (Any) –

Return type:

Plan