智能体开发领域正在迅速发展，LangChain也随之不断演变进化。虽然传统的LangChain智能体（尤其是基于AgentExecutor构建的）已经提供了稳定的服务，但LangGraph的出现带来了更为强大和灵活的解决方案。

本文指导读者如何将智能体迁移至LangGraph，使迁移后的智能体能够充分利用LangGraph的最新技术优势。

1 传统LangChain与LangGraph

传统LangChain智能体是基于AgentExecutor类构建的，为LangChain平台中的智能体开发提供了一种结构化的方法，并为智能体的行为提供了全面的配置选项。

LangGraph代表了LangChain智能体开发的新纪元。它赋予了开发者构建高度定制化和可控智能体的能力。与之前的版本相比，LangGraph提供了更为精细的控制能力。

2 为什么迁移至LangGraph

迁移至LangGraph可以解锁多个好处：

3 代码实现

下面是将传统LangChain智能体迁移到LangGraph所需的代码级别更改。

步骤I：安装库

pip install -U langgraph langchain langchain-openai

步骤II：智能体的基本使用

from langchain.agents import AgentExecutor, create_tool_calling_agentfrom langchain.memory import ChatMessageHistoryfrom langchain_core.prompts import ChatPromptTemplatefrom langchain_core.runnables.history import RunnableWithMessageHistoryfrom langchain_core.tools import toolfrom langchain_openai import ChatOpenAImodel = ChatOpenAI(model="gpt-4o")memory = ChatMessageHistory(session_id="test-session")prompt = ChatPromptTemplate.from_messages([("system", "You are a helpful assistant."),# First put the history("placeholder", "{chat_history}"),# Then the new input("human", "{input}"),# Finally the scratchpad("placeholder", "{agent_scratchpad}"),])@tooldef magic_function(input: int) -> int:"""Applies a magic function to an input."""return input + 2tools = [magic_function]agent = create_tool_calling_agent(model, tools, prompt)agent_executor = AgentExecutor(agent=agent, tools=tools)agent_with_chat_history = RunnableWithMessageHistory(agent_executor,# 这是必需的,因为在大多数现实场景中,需要一个会话ID# 但在这里没有真正使用,因为使用的是简单的内存ChatMessageHistorylambda session_id: memory,input_messages_key="input",history_messages_key="chat_history",)config = {"configurable": {"session_id": "test-session"}}print(agent_with_chat_history.invoke({"input": "Hi, I'm polly! What's the output of magic_function of 3?"}, config)["output"])print("---")print(agent_with_chat_history.invoke({"input": "Remember my name?"}, config)["output"])print("---")print(agent_with_chat_history.invoke({"input": "what was that output again?"}, config)["output"])# 输出Hi Polly! The output of the magic function for the input 3 is 5.---Yes, I remember your name, Polly! How can I assist you further?---The output of the magic function for the input 3 is 5.

步骤III：LangGraph的智能体状态管理

from langchain_core.messages import SystemMessagefrom langgraph.checkpoint import MemorySaver# 内存中的检查点保存器from langgraph.prebuilt import create_react_agentsystem_message = "You are a helpful assistant."# 这也可以是一个SystemMessage对象# system_message = SystemMessage(content="You are a helpful assistant. Respond only in Spanish.")memory = MemorySaver()app = create_react_agent(model, tools, messages_modifier=system_message, checkpointer=memory)config = {"configurable": {"thread_id": "test-thread"}}print(app.invoke({"messages": [("user", "Hi, I'm polly! What's the output of magic_function of 3?")]},config,)["messages"][-1].content)print("---")print(app.invoke({"messages": [("user", "Remember my name?")]}, config)["messages"][-1].content)print("---")print(app.invoke({"messages": [("user", "what was that output again?")]}, config)["messages"][-1].content)# 输出Hi Polly! The output of the magic_function for the input 3 is 5.---Yes, your name is Polly!---The output of the magic_function for the input 3 was 5.

4 结语

迁移至LangGraph的智能体会获得更深层次的能力和灵活性。按照既定步骤并理解系统消息的概念，将有助于实现平滑过渡，并优化智能体的性能表现。

本文转载自​​，作者：