langchain.agents.openai_tools.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_core.utils.function_calling import convert_to_openai_tool

from langchain.agents.format_scratchpad.openai_tools import (
    format_to_openai_tool_messages,
)
from langchain.agents.output_parsers.openai_tools import OpenAIToolsAgentOutputParser


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

参数：
    llm：作为代理使用的LLM。
    tools：此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Prompt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AgentAction或AgentFinish。

示例：

    .. code-block:: python

        from langchain import hub
        from langchain_community.chat_models import ChatOpenAI
        from langchain.agents import AgentExecutor, create_openai_tools_agent

        prompt = hub.pull("hwchase17/openai-tools-agent")
        model = ChatOpenAI()
        tools = ...

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

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

        # 使用聊天历史记录
        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?"),
                ],
            }
        )

Prompt：

    代理提示必须具有一个`agent_scratchpad`键，该键是一个``MessagesPlaceholder``。中间代理操作和工具输出消息将在此处传递。

    这是一个示例：

    .. code-block:: python

        from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

        prompt = ChatPromptTemplate.from_messages(
            [
                ("system", "You are a helpful assistant"),
                MessagesPlaceholder("chat_history", optional=True),
                ("human", "{input}"),
                MessagesPlaceholder("agent_scratchpad"),
            ]
        )
"""
    missing_vars = {"agent_scratchpad"}.difference(
        prompt.input_variables + list(prompt.partial_variables)
    )
    if missing_vars:
        raise ValueError(f"Prompt missing required variables: {missing_vars}")

    llm_with_tools = llm.bind(tools=[convert_to_openai_tool(tool) for tool in tools])

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