langchain.agents.tool_calling_agent.base — 🦜🔗 LangChain 0.2.0

from typing import Sequence

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

from langchain.agents.format_scratchpad.tools import (
    format_to_tool_messages,
)
from langchain.agents.output_parsers.tools import ToolsAgentOutputParser


[docs]def create_tool_calling_agent(
    llm: BaseLanguageModel, tools: Sequence[BaseTool], prompt: ChatPromptTemplate
) -> Runnable:
    """创建一个使用工具的代理。

参数:
    llm: 作为代理使用的LLM。
    tools: 该代理可以访问的工具。
    prompt: 要使用的提示。有关预期输入变量的更多信息，请参见下面的提示部分。

返回:
    代表代理的可运行序列。它接受与传入的提示相同的所有输入变量。它返回一个AgentAction或AgentFinish。

示例:

    .. code-block:: python

        from langchain.agents import AgentExecutor, create_tool_calling_agent, tool
        from langchain_anthropic import ChatAnthropic
        from langchain_core.prompts import ChatPromptTemplate

        prompt = ChatPromptTemplate.from_messages(
            [
                ("system", "You are a helpful assistant"),
                ("placeholder", "{chat_history}"),
                ("human", "{input}"),
                ("placeholder", "{agent_scratchpad}"),
            ]
        )
        model = ChatAnthropic(model="claude-3-opus-20240229")

        @tool
        def magic_function(input: int) -> int:
            \"\"\"对输入应用一个魔术函数。\"\"\"
            return input + 2

        tools = [magic_function]

        agent = create_tool_calling_agent(model, tools, prompt)
        agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

        agent_executor.invoke({"input": "what is the value of magic_function(3)?"})

        # 使用聊天历史
        from langchain_core.messages import AIMessage, HumanMessage
        agent_executor.invoke(
            {
                "input": "what's my name?",
                "chat_history": [
                    HumanMessage(content="hi! my name is bob"),
                    AIMessage(content="Hello Bob! How can I assist you today?"),
                ],
            }
        )

提示:

    代理提示必须有一个`agent_scratchpad`键，它是一个``MessagesPlaceholder``。中间代理操作和工具输出消息将传递到这里。
"""
    missing_vars = {"agent_scratchpad"}.difference(
        prompt.input_variables + list(prompt.partial_variables)
    )
    if missing_vars:
        raise ValueError(f"Prompt missing required variables: {missing_vars}")

    if not hasattr(llm, "bind_tools"):
        raise ValueError(
            "This function requires a .bind_tools method be implemented on the LLM.",
        )
    llm_with_tools = llm.bind_tools(tools)

    agent = (
        RunnablePassthrough.assign(
            agent_scratchpad=lambda x: format_to_tool_messages(x["intermediate_steps"])
        )
        | prompt
        | llm_with_tools
        | ToolsAgentOutputParser()
    )
    return agent
Source code for langchain.agents.tool_calling_agent.base
