LangGraph快速入门

一切尽在，你来2026-02-18 17:47

快速开始

本快速入门教程将演示如何使用 LangGraph 图 API 或函数式 API 构建一个计算器智能体。

  • 如果你希望将智能体定义为节点与边的图结构，请使用图 API。

  • 如果你希望将智能体定义为单个函数，请使用函数式 API。

使用图 API

1. 定义工具和模型

本示例中，我们将使用 Claude Sonnet 4.5 模型，并定义加法、乘法、除法工具。

python 复制代码 
from langchain.tools import tool
from langchain.chat_models import init_chat_model


model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    temperature=0
)


# 定义工具
@tool
def multiply(a: int, b: int) -> int:
    """Multiply `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a * b


@tool
def add(a: int, b: int) -> int:
    """Adds `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a + b


@tool
def divide(a: int, b: int) -> float:
    """Divide `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a / b


# 为大模型绑定工具
tools = [add, multiply, divide]
tools_by_name = {tool.name: tool for tool in tools}
model_with_tools = model.bind_tools(tools)

2. 定义状态

图的状态用于存储消息和大模型调用次数。

LangGraph 中的状态在整个智能体执行过程中保持持久化。

使用带 operator.add 的 Annotated 类型可以确保新消息追加到现有列表，而不是替换列表。

python 复制代码 
from langchain.messages import AnyMessage
from typing_extensions import TypedDict, Annotated
import operator


class MessagesState(TypedDict):
    messages: Annotated[list[AnyMessage], operator.add]
    llm_calls: int

3. 定义模型节点

模型节点用于调用大模型，并决定是否调用工具。

python 复制代码 
from langchain.messages import SystemMessage


def llm_call(state: dict):
    """LLM decides whether to call a tool or not"""

    return {
        "messages": [
            model_with_tools.invoke(
                [
                    SystemMessage(
                        content="You are a helpful assistant tasked with performing arithmetic on a set of inputs."
                    )
                ]
                + state["messages"]
            )
        ],
        "llm_calls": state.get('llm_calls', 0) + 1
    }

4. 定义工具节点

工具节点用于执行工具调用并返回结果。

python 复制代码 
from langchain.messages import ToolMessage


def tool_node(state: dict):
    """Performs the tool call"""

    result = []
    for tool_call in state["messages"][-1].tool_calls:
        tool = tools_by_name[tool_call["name"]]
        observation = tool.invoke(tool_call["args"])
        result.append(ToolMessage(content=observation, tool_call_id=tool_call["id"]))
    return {"messages": result}

5. 定义结束逻辑

条件边函数根据大模型是否发起工具调用，来决定路由到工具节点或直接结束。

python 复制代码 
from typing import Literal
from langgraph.graph import StateGraph, START, END


def should_continue(state: MessagesState) -> Literal["tool_node", END]:
    """Decide if we should continue the loop or stop based upon whether the LLM made a tool call"""

    messages = state["messages"]
    last_message = messages[-1]

    # 如果 LLM 调用了工具，则执行动作
    if last_message.tool_calls:
        return "tool_node"

    # 否则停止（回复用户）
    return END

6. 构建并编译智能体

使用 StateGraph 类构建智能体，并使用 compile 方法编译。

python 复制代码 
# 构建工作流
agent_builder = StateGraph(MessagesState)

# 添加节点
agent_builder.add_node("llm_call", llm_call)
agent_builder.add_node("tool_node", tool_node)

# 添加边连接节点
agent_builder.add_edge(START, "llm_call")
agent_builder.add_conditional_edges(
    "llm_call",
    should_continue,
    ["tool_node", END]
)
agent_builder.add_edge("tool_node", "llm_call")

# 编译智能体
agent = agent_builder.compile()

# 展示智能体结构图
from IPython.display import Image, display
display(Image(agent.get_graph(xray=True).draw_mermaid_png()))

# 调用
from langchain.messages import HumanMessage
messages = [HumanMessage(content="Add 3 and 4.")]
messages = agent.invoke({"messages": messages})
for m in messages["messages"]:
    m.pretty_print()

如需了解如何使用 LangSmith 追踪智能体，请查看 LangSmith 文档。

恭喜！你已经使用 LangGraph 图 API 构建了第一个智能体。
完整代码示例

python 复制代码 
# Step 1: Define tools and model

from langchain.tools import tool
from langchain.chat_models import init_chat_model


model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    temperature=0
)


# Define tools
@tool
def multiply(a: int, b: int) -> int:
    """Multiply `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a * b


@tool
def add(a: int, b: int) -> int:
    """Adds `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a + b


@tool
def divide(a: int, b: int) -> float:
    """Divide `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a / b


# Augment the LLM with tools
tools = [add, multiply, divide]
tools_by_name = {tool.name: tool for tool in tools}
model_with_tools = model.bind_tools(tools)

# Step 2: Define state

from langchain.messages import AnyMessage
from typing_extensions import TypedDict, Annotated
import operator


class MessagesState(TypedDict):
    messages: Annotated[list[AnyMessage], operator.add]
    llm_calls: int

# Step 3: Define model node
from langchain.messages import SystemMessage


def llm_call(state: dict):
    """LLM decides whether to call a tool or not"""

    return {
        "messages": [
            model_with_tools.invoke(
                [
                    SystemMessage(
                        content="You are a helpful assistant tasked with performing arithmetic on a set of inputs."
                    )
                ]
                + state["messages"]
            )
        ],
        "llm_calls": state.get('llm_calls', 0) + 1
    }


# Step 4: Define tool node

from langchain.messages import ToolMessage


def tool_node(state: dict):
    """Performs the tool call"""

    result = []
    for tool_call in state["messages"][-1].tool_calls:
        tool = tools_by_name[tool_call["name"]]
        observation = tool.invoke(tool_call["args"])
        result.append(ToolMessage(content=observation, tool_call_id=tool_call["id"]))
    return {"messages": result}

# Step 5: Define logic to determine whether to end

from typing import Literal
from langgraph.graph import StateGraph, START, END


# Conditional edge function to route to the tool node or end based upon whether the LLM made a tool call
def should_continue(state: MessagesState) -> Literal["tool_node", END]:
    """Decide if we should continue the loop or stop based upon whether the LLM made a tool call"""

    messages = state["messages"]
    last_message = messages[-1]

    # If the LLM makes a tool call, then perform an action
    if last_message.tool_calls:
        return "tool_node"

    # Otherwise, we stop (reply to the user)
    return END

# Step 6: Build agent

# Build workflow
agent_builder = StateGraph(MessagesState)

# Add nodes
agent_builder.add_node("llm_call", llm_call)
agent_builder.add_node("tool_node", tool_node)

# Add edges to connect nodes
agent_builder.add_edge(START, "llm_call")
agent_builder.add_conditional_edges(
    "llm_call",
    should_continue,
    ["tool_node", END]
)
agent_builder.add_edge("tool_node", "llm_call")

# Compile the agent
agent = agent_builder.compile()


from IPython.display import Image, display
# Show the agent
display(Image(agent.get_graph(xray=True).draw_mermaid_png()))

# Invoke
from langchain.messages import HumanMessage
messages = [HumanMessage(content="Add 3 and 4.")]
messages = agent.invoke({"messages": messages})
for m in messages["messages"]:
    m.pretty_print()

使用函数式 API

1. 定义工具和模型

本示例中，我们将使用 Claude Sonnet 4.5 模型，并定义加法、乘法、除法工具。

python 复制代码 
from langchain.tools import tool
from langchain.chat_models import init_chat_model


model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    temperature=0
)


# Define tools
@tool
def multiply(a: int, b: int) -> int:
    """Multiply `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a * b


@tool
def add(a: int, b: int) -> int:
    """Adds `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a + b


@tool
def divide(a: int, b: int) -> float:
    """Divide `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a / b


# Augment the LLM with tools
tools = [add, multiply, divide]
tools_by_name = {tool.name: tool for tool in tools}
model_with_tools = model.bind_tools(tools)

from langgraph.graph import add_messages
from langchain.messages import (
    SystemMessage,
    HumanMessage,
    ToolCall,
)
from langchain_core.messages import BaseMessage
from langgraph.func import entrypoint, task

2. 定义模型节点

模型节点用于调用大模型，并决定是否调用工具。

@task 装饰器将函数标记为可在智能体中执行的任务。任务可以在入口函数中同步或异步调用。

python 复制代码 
@task
def call_llm(messages: list[BaseMessage]):
    """LLM decides whether to call a tool or not"""
    return model_with_tools.invoke(
        [
            SystemMessage(
                content="You are a helpful assistant tasked with performing arithmetic on a set of inputs."
            )
        ]
        + messages
    )

3. 定义工具节点

工具节点用于执行工具调用并返回结果。

python 复制代码 
@task
def call_tool(tool_call: ToolCall):
    """Performs the tool call"""
    tool = tools_by_name[tool_call["name"]]
    return tool.invoke(tool_call)

4. 定义智能体

使用 @entrypoint 函数构建智能体。

在函数式 API 中，你不需要显式定义节点和边，而是在单个函数中编写标准的控制流逻辑（循环、条件判断）。

python 复制代码 
@entrypoint()
def agent(messages: list[BaseMessage]):
    model_response = call_llm(messages).result()

    while True:
        if not model_response.tool_calls:
            break

        # Execute tools
        tool_result_futures = [
            call_tool(tool_call) for tool_call in model_response.tool_calls
        ]
        tool_results = [fut.result() for fut in tool_result_futures]
        messages = add_messages(messages, [model_response, *tool_results])
        model_response = call_llm(messages).result()

    messages = add_messages(messages, model_response)
    return messages

# Invoke
messages = [HumanMessage(content="Add 3 and 4.")]
for chunk in agent.stream(messages, stream_mode="updates"):
    print(chunk)
    print("\n")

如需了解如何使用 LangSmith 追踪智能体，请查看 LangSmith 文档。

恭喜！你已经使用 LangGraph 函数式 API 构建了第一个智能体。
完整代码示例

python 复制代码 
# Step 1: Define tools and model

from langchain.tools import tool
from langchain.chat_models import init_chat_model


model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    temperature=0
)


# Define tools
@tool
def multiply(a: int, b: int) -> int:
    """Multiply `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a * b


@tool
def add(a: int, b: int) -> int:
    """Adds `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a + b


@tool
def divide(a: int, b: int) -> float:
    """Divide `a` and `b`.

    Args:
        a: First int
        b: Second int
    """
    return a / b


# Augment the LLM with tools
tools = [add, multiply, divide]
tools_by_name = {tool.name: tool for tool in tools}
model_with_tools = model.bind_tools(tools)

from langgraph.graph import add_messages
from langchain.messages import (
    SystemMessage,
    HumanMessage,
    ToolCall,
)
from langchain_core.messages import BaseMessage
from langgraph.func import entrypoint, task


# Step 2: Define model node

@task
def call_llm(messages: list[BaseMessage]):
    """LLM decides whether to call a tool or not"""
    return model_with_tools.invoke(
        [
            SystemMessage(
                content="You are a helpful assistant tasked with performing arithmetic on a set of inputs."
            )
        ]
        + messages
    )


# Step 3: Define tool node

@task
def call_tool(tool_call: ToolCall):
    """Performs the tool call"""
    tool = tools_by_name[tool_call["name"]]
    return tool.invoke(tool_call)


# Step 4: Define agent

@entrypoint()
def agent(messages: list[BaseMessage]):
    model_response = call_llm(messages).result()

    while True:
        if not model_response.tool_calls:
            break

        # Execute tools
        tool_result_futures = [
            call_tool(tool_call) for tool_call in model_response.tool_calls
        ]
        tool_results = [fut.result() for fut in tool_result_futures]
        messages = add_messages(messages, [model_response, *tool_results])
        model_response = call_llm(messages).result()

    messages = add_messages(messages, model_response)
    return messages

# Invoke
messages = [HumanMessage(content="Add 3 and 4.")]
for chunk in agent.stream(messages, stream_mode="updates"):
    print(chunk)
    print("\n")
相关推荐
YuanDaima20481 天前
[CrewAI] 第15课|构建一个多代理系统来实现自动化简历定制和面试准备
人工智能·python·面试·agent·crewai
TDengine （老段）1 天前
TDengine IDMP 工业数据建模 —— 属性
大数据·数据库·人工智能·时序数据库·tdengine·涛思数据
WHS-_-20221 天前
Python 算法题学习笔记一
python·学习·算法
机器之心1 天前
京东卷出新高度！硬刚「复杂指令」长时长、自由态数字人直播终于丝滑了
人工智能·openai
机器之心1 天前
龙虾太难养？发布的SOLO独立端，可能是你要的AI生产力
人工智能·openai
码界筑梦坊1 天前
353-基于Python的大湾区气候数据可视化分析系统
开发语言·python·信息可视化·数据分析·django·vue·毕业设计
nancy_princess1 天前
attention基础概念1
人工智能
做个文艺程序员1 天前
华为昇腾NPU部署开源大模型全攻略（以Qwen3-8B为例）
人工智能·深度学习·华为
与虾牵手1 天前
Claude Tool Use 怎么用？从零到生产的完整教程（2026）
ai编程·claude
像我这样帅的人丶你还1 天前
从交稿到甩锅预防：AI 前端流水线
前端·ai编程
热门推荐
012026年3月AI领域大事件：DeepSeek引领开源风暴02GitHub 镜像站点03Qwen3.5-Omni与Qwen3.6模型全面解析（含测评/案例/使用教程）04围棋-html版本05纯 HTML/CSS/JS 实现的高颜值登录页，还会眨眼睛！少女心爆棚！06Claude Code + GLM4.7 避坑指南：解决 Unable to connect to Anthropic services07让 Trae IDE 智能体 “读懂”文档 Excel+PDF+DOCX ：mcp-documents-reader 工具使用指南08Mac 本地部署 OMLX + 通义千问 Qwen3.5-27B 保姆级教程09UV安装并设置国内源10“wsl --install -d Ubuntu-22.04”下载慢，中国地区离线安装 Ubuntu 22.04 WSL方法（亲测2025年5月6日）