langchain.js
    Preparing search index...

    Class ReActSingleInputOutputParser

    Parses ReAct-style LLM calls that have a single tool input.

    Expects output to be in one of two formats.

    If the output signals that an action should be taken, should be in the below format. This will result in an AgentAction being returned.

    Thought: agent thought here
    Action: search
    Action Input: what is the temperature in SF?

    If the output signals that a final answer should be given, should be in the below format. This will result in an AgentFinish being returned.

    Thought: agent thought here
    Final Answer: The temperature is 100 degrees


    const runnableAgent = RunnableSequence.from([
      ...rest of runnable
      new ReActSingleInputOutputParser({ toolNames: ["SerpAPI", "Calculator"] }),
    ]);
    const agent = AgentExecutor.fromAgentAndTools({
      agent: runnableAgent,
      tools: [new SerpAPI(), new Calculator()],
    });
    const result = await agent.invoke({
      input: "whats the weather in pomfret?",
    });

    Hierarchy (View Summary)

    Index

    Constructors

    constructor

    Properties

    lc_namespace

    Methods

    getFormatInstructions parse

    Constructors

    Properties

    lc_namespace: string[] = ...

    Methods

    • Returns the format instructions as a string. If the 'raw' option is true, returns the raw FORMAT_INSTRUCTIONS.

      Returns string

      Format instructions as a string.

    • Parses the given text into an AgentAction or AgentFinish object. If an output fixing parser is defined, uses it to parse the text.

      Parameters

      • text: string

        Text to parse.

      Returns Promise<any>

      Promise that resolves to an AgentAction or AgentFinish object.

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Methods