快速入门

本快速入门演示了如何使用LangGraph图API或功能API构建一个计算器智能体。

使用图API，如果您更喜欢将您的智能体定义为节点和边的图。
使用函数API，如果您更喜欢将您的智能体定义为单个函数。

对于这个示例，您需要设置一个 Claude (Anthropic) 账户并获取一个API密钥。然后，在您的终端中设置 ANTHROPIC_API_KEY 环境变量。

Use the Graph API
Use the Functional API

1. 定义工具和模型

在这个示例中，我们将使用Claude Sonnet 4.5模型，并定义加法、乘法和除法工具。

import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-5",
  temperature: 0,
});

// Define tools
const add = tool(({ a, b }) => a + b, {
  name: "add",
  description: "Add two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const multiply = tool(({ a, b }) => a * b, {
  name: "multiply",
  description: "Multiply two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const divide = tool(({ a, b }) => a / b, {
  name: "divide",
  description: "Divide two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

// Augment the LLM with tools
const toolsByName = {
  [add.name]: add,
  [multiply.name]: multiply,
  [divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);

2. 定义状态

图的状态用于存储消息和LLM调用的次数。

LangGraph中的状态在智能体的执行过程中持续存在。智能体类型 Annotated 与 operator.add 确保新消息被附加到现有列表中，而不是替换它。

import { StateGraph, START, END } from "@langchain/langgraph";
import { MessagesZodMeta } from "@langchain/langgraph";
import { registry } from "@langchain/langgraph/zod";
import { type BaseMessage } from "@langchain/core/messages";

const MessagesState = z.object({
  messages: z
    .array(z.custom<BaseMessage>())
    .register(registry, MessagesZodMeta),
  llmCalls: z.number().optional(),
});

3. 定义模型节点

模型节点用于调用LLM并决定是否调用工具。

import { SystemMessage } from "@langchain/core/messages";
async function llmCall(state: z.infer<typeof MessagesState>) {
  return {
    messages: await modelWithTools.invoke([
      new SystemMessage(
        "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
      ),
      ...state.messages,
    ]),
    llmCalls: (state.llmCalls ?? 0) + 1,
  };
}

4. 定义工具节点

工具节点用于调用工具并返回结果。

import { isAIMessage, ToolMessage } from "@langchain/core/messages";
async function toolNode(state: z.infer<typeof MessagesState>) {
  const lastMessage = state.messages.at(-1);

  if (lastMessage == null || !isAIMessage(lastMessage)) {
    return { messages: [] };
  }

  const result: ToolMessage[] = [];
  for (const toolCall of lastMessage.tool_calls ?? []) {
    const tool = toolsByName[toolCall.name];
    const observation = await tool.invoke(toolCall);
    result.push(observation);
  }

  return { messages: result };
}

5. 定义结束逻辑

条件边函数用于根据LLM是否调用了工具来路由到工具节点或终点。

async function shouldContinue(state: z.infer<typeof MessagesState>) {
  const lastMessage = state.messages.at(-1);
  if (lastMessage == null || !isAIMessage(lastMessage)) return END;

  // If the LLM makes a tool call, then perform an action
  if (lastMessage.tool_calls?.length) {
    return "toolNode";
  }

  // Otherwise, we stop (reply to the user)
  return END;
}

6. 构建和编译智能体

智能体是使用StateGraph类构建的，并使用@[compile][StateGraph.compile]方法编译。

const agent = new StateGraph(MessagesState)
  .addNode("llmCall", llmCall)
  .addNode("toolNode", toolNode)
  .addEdge(START, "llmCall")
  .addConditionalEdges("llmCall", shouldContinue, ["toolNode", END])
  .addEdge("toolNode", "llmCall")
  .compile();

// Invoke
import { HumanMessage } from "@langchain/core/messages";
const result = await agent.invoke({
  messages: [new HumanMessage("Add 3 and 4.")],
});

for (const message of result.messages) {
  console.log(`[${message.getType()}]: ${message.text}`);
}

恭喜您！您已使用LangGraph图API构建了您的第一个智能体。

Full code example

// Step 1: Define tools and model

import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-5",
  temperature: 0,
});

// Define tools
const add = tool(({ a, b }) => a + b, {
  name: "add",
  description: "Add two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const multiply = tool(({ a, b }) => a * b, {
  name: "multiply",
  description: "Multiply two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const divide = tool(({ a, b }) => a / b, {
  name: "divide",
  description: "Divide two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

// Augment the LLM with tools
const toolsByName = {
  [add.name]: add,
  [multiply.name]: multiply,
  [divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);

// Step 2: Define state

import { StateGraph, START, END } from "@langchain/langgraph";
import { MessagesZodMeta } from "@langchain/langgraph";
import { registry } from "@langchain/langgraph/zod";
import { type BaseMessage } from "@langchain/core/messages";

const MessagesState = z.object({
  messages: z
    .array(z.custom<BaseMessage>())
    .register(registry, MessagesZodMeta),
  llmCalls: z.number().optional(),
});

// Step 3: Define model node

import { SystemMessage } from "@langchain/core/messages";
async function llmCall(state: z.infer<typeof MessagesState>) {
  return {
    messages: await modelWithTools.invoke([
      new SystemMessage(
        "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
      ),
      ...state.messages,
    ]),
    llmCalls: (state.llmCalls ?? 0) + 1,
  };
}

// Step 4: Define tool node

import { isAIMessage, ToolMessage } from "@langchain/core/messages";
async function toolNode(state: z.infer<typeof MessagesState>) {
  const lastMessage = state.messages.at(-1);

  if (lastMessage == null || !isAIMessage(lastMessage)) {
    return { messages: [] };
  }

  const result: ToolMessage[] = [];
  for (const toolCall of lastMessage.tool_calls ?? []) {
    const tool = toolsByName[toolCall.name];
    const observation = await tool.invoke(toolCall);
    result.push(observation);
  }

  return { messages: result };
}

// Step 5: Define logic to determine whether to end

async function shouldContinue(state: z.infer<typeof MessagesState>) {
  const lastMessage = state.messages.at(-1);
  if (lastMessage == null || !isAIMessage(lastMessage)) return END;

  // If the LLM makes a tool call, then perform an action
  if (lastMessage.tool_calls?.length) {
    return "toolNode";
  }

  // Otherwise, we stop (reply to the user)
  return END;
}

// Step 6: Build and compile the agent

const agent = new StateGraph(MessagesState)
  .addNode("llmCall", llmCall)
  .addNode("toolNode", toolNode)
  .addEdge(START, "llmCall")
  .addConditionalEdges("llmCall", shouldContinue, ["toolNode", END])
  .addEdge("toolNode", "llmCall")
  .compile();

// Invoke
import { HumanMessage } from "@langchain/core/messages";
const result = await agent.invoke({
  messages: [new HumanMessage("Add 3 and 4.")],
});

for (const message of result.messages) {
  console.log(`[${message.getType()}]: ${message.text}`);
}

1. 定义工具和模型

在这个示例中，我们将使用Claude Sonnet 4.5模型，并定义加法、乘法和除法工具。

import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-5",
  temperature: 0,
});

// Define tools
const add = tool(({ a, b }) => a + b, {
  name: "add",
  description: "Add two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const multiply = tool(({ a, b }) => a * b, {
  name: "multiply",
  description: "Multiply two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const divide = tool(({ a, b }) => a / b, {
  name: "divide",
  description: "Divide two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

// Augment the LLM with tools
const toolsByName = {
  [add.name]: add,
  [multiply.name]: multiply,
  [divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);

2. 定义模型节点

模型节点用于调用LLM并决定是否调用工具。

使用 @[@task] 装饰器将一个函数标记为可以作为智能体的一部分执行的任务。任务可以在您的入口函数中同步或异步调用。

import { task, entrypoint } from "@langchain/langgraph";
import { SystemMessage } from "@langchain/core/messages";
const callmodel = task({ name: "callLlm" }, async (messages: BaseMessage[]) => {
  return modelWithTools.invoke([
    new SystemMessage(
      "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
    ),
    ...messages,
  ]);
});

3. 定义工具节点

工具节点用于调用工具并返回结果。

import type { ToolCall } from "@langchain/core/messages/tool";
const callTool = task({ name: "callTool" }, async (toolCall: ToolCall) => {
  const tool = toolsByName[toolCall.name];
  return tool.invoke(toolCall);
});

4. 定义智能体

智能体是通过使用@[@entrypoint]函数构建的。

在功能API中，您不需要显式定义节点和边，而是在单个函数内编写标准的控制流逻辑（循环、条件语句）。

import { addMessages } from "@langchain/langgraph";
import { type BaseMessage, isAIMessage } from "@langchain/core/messages";

const agent = entrypoint({ name: "agent" }, async (messages: BaseMessage[]) => {
  let modelResponse = await callLlm(messages);

  while (true) {
    if (!modelResponse.tool_calls?.length) {
      break;
    }

    // Execute tools
    const toolResults = await Promise.all(
      modelResponse.tool_calls.map((toolCall) => callTool(toolCall))
    );
    messages = addMessages(messages, [modelResponse, ...toolResults]);
    modelResponse = await callLlm(messages);
  }

  return messages;
});

// Invoke
import { HumanMessage } from "@langchain/core/messages";

const result = await agent.invoke([new HumanMessage("Add 3 and 4.")]);

for (const message of result) {
  console.log(`[${message.getType()}]: ${message.text}`);
}

恭喜您！您已使用LangGraph功能API构建了您的第一个智能体。

Full code example

// Step 1: Define tools and model

import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-5",
  temperature: 0,
});

// Define tools
const add = tool(({ a, b }) => a + b, {
  name: "add",
  description: "Add two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const multiply = tool(({ a, b }) => a * b, {
  name: "multiply",
  description: "Multiply two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

const divide = tool(({ a, b }) => a / b, {
  name: "divide",
  description: "Divide two numbers",
  schema: z.object({
    a: z.number().describe("First number"),
    b: z.number().describe("Second number"),
  }),
});

// Augment the LLM with tools
const toolsByName = {
  [add.name]: add,
  [multiply.name]: multiply,
  [divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);

// Step 2: Define model node

import { task, entrypoint } from "@langchain/langgraph";
import { SystemMessage } from "@langchain/core/messages";
const callmodel = task({ name: "callLlm" }, async (messages: BaseMessage[]) => {
  return modelWithTools.invoke([
    new SystemMessage(
      "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
    ),
    ...messages,
  ]);
});

// Step 3: Define tool node

import type { ToolCall } from "@langchain/core/messages/tool";
const callTool = task({ name: "callTool" }, async (toolCall: ToolCall) => {
  const tool = toolsByName[toolCall.name];
  return tool.invoke(toolCall);
});

// Step 4: Define agent
import { addMessages } from "@langchain/langgraph";
import { type BaseMessage, isAIMessage } from "@langchain/core/messages";
const agent = entrypoint({ name: "agent" }, async (messages: BaseMessage[]) => {
  let modelResponse = await callLlm(messages);

  while (true) {
    if (!modelResponse.tool_calls?.length) {
      break;
    }

    // Execute tools
    const toolResults = await Promise.all(
      modelResponse.tool_calls.map((toolCall) => callTool(toolCall))
    );
    messages = addMessages(messages, [modelResponse, ...toolResults]);
    modelResponse = await callLlm(messages);
  }

  return messages;
});

// Invoke
import { HumanMessage } from "@langchain/core/messages";
const result = await agent.invoke([new HumanMessage("Add 3 and 4.")]);

for (const message of result) {
  console.log(`[${message.getType()}]: ${message.text}`);
}

在GitHub上编辑此页面的源代码。

通过MCP将这些文档编程连接到Claude、VSCode等，以获取实时答案。

LangGraph v1.0

开始使用

功能特性

生产环境

LangGraph APIs

1. 定义工具和模型

2. 定义状态

3. 定义模型节点

4. 定义工具节点

5. 定义结束逻辑

6. 构建和编译智能体

1. 定义工具和模型

2. 定义模型节点

3. 定义工具节点

4. 定义智能体

LangGraph v1.0

开始使用

功能特性

生产环境

LangGraph APIs

​1. 定义工具和模型

​2. 定义状态

​3. 定义模型节点

​4. 定义工具节点

​5. 定义结束逻辑

​6. 构建和编译智能体

​1. 定义工具和模型

​2. 定义模型节点

​3. 定义工具节点

​4. 定义智能体

1. 定义工具和模型

2. 定义状态

3. 定义模型节点

4. 定义工具节点

5. 定义结束逻辑

6. 构建和编译智能体

1. 定义工具和模型

2. 定义模型节点

3. 定义工具节点

4. 定义智能体