langchain.js
    Preparing search index...

    Class representing a plan-and-execute agent executor. This agent decides on the full sequence of actions upfront, then executes them all without updating the plan. This is suitable for complex or long-running tasks that require maintaining long-term objectives and focus.

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    memory?: any

    Accessors

    • get inputKeys(): string[]

      Returns string[]

    • get lc_namespace(): string[]

      Returns string[]

    • get outputKeys(): string[]

      Returns string[]

    Methods

    • Return the string type key uniquely identifying this class of chain.

      Returns "agent_executor"

    • Parameters

      • values: any

      Returns Promise<any>

    • Parameters

      • inputs: ChainValues[]
      • Optionalconfig: any[]

      Returns Promise<ChainValues[]>

      Use .batch() instead. Will be removed in 0.2.0.

      Call the chain on all inputs in the list

    • Parameters

      • values: any
      • Optionalconfig: any
      • Optionaltags: string[]

      Returns Promise<ChainValues>

      Use .invoke() instead. Will be removed in 0.2.0.

      Run the core logic of this chain and add to output if desired.

      Wraps _call and handles memory.

    • Invoke the chain with the provided input and returns the output.

      Parameters

      • input: ChainValues

        Input values for the chain run.

      • Optionaloptions: any

      Returns Promise<ChainValues>

      Promise that resolves with the output of the chain run.

    • Parameters

      • inputs: Record<string, unknown>
      • outputs: Record<string, unknown>
      • returnOnlyOutputs: boolean = false

      Returns Promise<Record<string, unknown>>

    • Parameters

      • input: any
      • Optionalconfig: any

      Returns Promise<string>

      Use .invoke() instead. Will be removed in 0.2.0.

    • Load a chain from a json-like object describing it.

      Parameters

      Returns Promise<BaseChain<ChainValues, ChainValues>>

    • Static method that creates a new PlanAndExecuteAgentExecutor from a given LLM, a set of tools, and optionally a human message template. It uses the getDefaultPlanner and getDefaultStepExecutor methods to create the planner and step executor for the new agent executor.

      Parameters

      • __namedParameters: {
            humanMessageTemplate?: string;
            llm: BaseLanguageModelInterface;
            tools: Tool[] | DynamicStructuredTool[];
        } & Omit<PlanAndExecuteAgentExecutorInput, "planner" | "stepExecutor">

      Returns Promise<PlanAndExecuteAgentExecutor>

      A new PlanAndExecuteAgentExecutor instance.

    • Static method that returns a default planner for the agent. It creates a new LLMChain with a given LLM and a fixed prompt, and uses it to create a new LLMPlanner with a PlanOutputParser.

      Parameters

      • llm: { llm: BaseLanguageModelInterface; tools: Tool[] | DynamicStructuredTool[] }

        The Large Language Model (LLM) used to generate responses.

      Returns Promise<LLMPlanner>

      A new LLMPlanner instance.

    • Static method that returns a default step executor for the agent. It creates a new ChatAgent from a given LLM and a set of tools, and uses it to create a new ChainStepExecutor.

      Parameters

      • __namedParameters: {
            humanMessageTemplate?: string;
            llm: BaseLanguageModelInterface;
            tools: Tool[] | DynamicStructuredTool[];
        }

      Returns ChainStepExecutor

      A new ChainStepExecutor instance.

    • Returns string