从LangChain升级LangGraph，大幅提升智能体性能

小虎哦哦

发布于 2024-10-24 14:59

浏览

0收藏

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：

控制力提升：LangGraph提供了对智能体决策过程的更大控制权，可以更精确地定制其响应和动作。
架构灵活性：LangGraph的架构设计更为灵活，开发者可以根据特定需求设计出完美的智能体。
技术前瞻性：LangChain正在积极推进开发LangGraph，预示着平台内智能体创建的未来方向。及时迁移能够确保智能体技术始终处于行业前沿。

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_agent
from langchain.memory import ChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = 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}"),
    ]
)


@tool
def magic_function(input: int) -> int:
    """Applies a magic function to an input."""
    return input + 2


tools = [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ChatMessageHistory
    lambda 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 SystemMessage
from langgraph.checkpoint import MemorySaver  # 内存中的检查点保存器
from langgraph.prebuilt import create_react_agent

system_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.