Source code for langchain.agents.react.agent

from __future__ import annotations

from typing import Optional, Sequence

from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate
from langchain_core.runnables import Runnable, RunnablePassthrough
from langchain_core.tools import BaseTool

from langchain.agents import AgentOutputParser
from langchain.agents.format_scratchpad import format_log_to_str
from langchain.agents.output_parsers import ReActSingleInputOutputParser
from langchain.tools.render import ToolsRenderer, render_text_description


def create_react_agent(
    llm: BaseLanguageModel,
    tools: Sequence[BaseTool],
    prompt: BasePromptTemplate,
    output_parser: Optional[AgentOutputParser] = None,
    tools_renderer: ToolsRenderer = render_text_description,
) -> Runnable:
    """Create an agent that uses ReAct prompting.

    Args:
        llm: LLM to use as the agent.
        tools: Tools this agent has access to.
        prompt: The prompt to use. See Prompt section below for more.
        output_parser: AgentOutputParser for parse the LLM output.
        tools_renderer: This controls how the tools are converted into a string and
            then passed into the LLM. Default is `render_text_description`.

    Returns:
        A Runnable sequence representing an agent. It takes as input all the same input
        variables as the prompt passed in does. It returns as output either an
        AgentAction or AgentFinish.

    Examples:

        .. code-block:: python

            from langchain import hub
            from langchain_community.llms import OpenAI
            from langchain.agents import AgentExecutor, create_react_agent

            prompt = hub.pull("hwchase17/react")
            model = OpenAI()
            tools = ...

            agent = create_react_agent(model, tools, prompt)
            agent_executor = AgentExecutor(agent=agent, tools=tools)

            agent_executor.invoke({"input": "hi"})

            # Use with chat history
            from langchain_core.messages import AIMessage, HumanMessage
            agent_executor.invoke(
                {
                    "input": "what's my name?",
                    # Notice that chat_history is a string
                    # since this prompt is aimed at LLMs, not chat models
                    "chat_history": "Human: My name is Bob\nAI: Hello Bob!",
                }
            )

    Prompt:

        The prompt must have input keys:
            * `tools`: contains descriptions and arguments for each tool.
            * `tool_names`: contains all tool names.
            * `agent_scratchpad`: contains previous agent actions and tool outputs as a string.

        Here's an example:

        .. code-block:: python

            from langchain_core.prompts import PromptTemplate

            template = '''Answer the following questions as best you can. You have access to the following tools:

            {tools}

            Use the following format:

            Question: the input question you must answer
            Thought: you should always think about what to do
            Action: the action to take, should be one of [{tool_names}]
            Action Input: the input to the action
            Observation: the result of the action
            ... (this Thought/Action/Action Input/Observation can repeat N times)
            Thought: I now know the final answer
            Final Answer: the final answer to the original input question

            Begin!

            Question: {input}
            Thought:{agent_scratchpad}'''

            prompt = PromptTemplate.from_template(template)
    """  # noqa: E501
    missing_vars = {"tools", "tool_names", "agent_scratchpad"}.difference(
        prompt.input_variables
    )
    if missing_vars:
        raise ValueError(f"Prompt missing required variables: {missing_vars}")

    prompt = prompt.partial(
        tools=tools_renderer(list(tools)),
        tool_names=", ".join([t.name for t in tools]),
    )
    llm_with_stop = llm.bind(stop=["\nObservation"])
    output_parser = output_parser or ReActSingleInputOutputParser()
    agent = (
        RunnablePassthrough.assign(
            agent_scratchpad=lambda x: format_log_to_str(x["intermediate_steps"]),
        )
        | prompt
        | llm_with_stop
        | output_parser
    )
    return agent