快速入门 - 以编程方式使用文档

本快速入门演示了如何使用 LangGraph Graph API 或 Functional API 构建计算器代理。

- 使用 Graph API 如果您更喜欢将代理定义为节点和边的图。
- 使用 Functional API 如果您更喜欢将代理定义为单个函数。

有关概念信息，请参阅 Graph API 概述和 Functional API 概述.

Use the Graph API

1. 定义工具和模型

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

const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  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 state 用于存储消息和 LLM 调用次数。

  StateGraph,
  StateSchema,
  MessagesValue,
  ReducedValue,
  GraphNode,
  ConditionalEdgeRouter,
  START,
  END,
} from "@langchain/langgraph";


const MessagesState = new StateSchema({
  messages: MessagesValue,
  llmCalls: new ReducedValue(
    z.number().default(0),
    { reducer: (x, y) => x + y }
  ),
});

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。

const llmCall: GraphNode<typeof MessagesState> = async (state) => {
  const response = await modelWithTools.invoke([
    new SystemMessage(
      "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
    ),
    ...state.messages,
  ]);
  return {
    messages: [response],
    llmCalls: 1,
  };
};

4. 定义工具节点

工具节点用于调用工具并返回结果。

const toolNode: GraphNode<typeof MessagesState> = async (state) => {
  const lastMessage = state.messages.at(-1);

  if (lastMessage == null || !AIMessage.isInstance(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 是否进行了工具调用来路由到工具节点或结束。

const shouldContinue: ConditionalEdgeRouter<typeof MessagesState, "toolNode"> = (state) => {
  const lastMessage = state.messages.at(-1);

  // Check if it's an AIMessage before accessing tool_calls
  if (!lastMessage || !AIMessage.isInstance(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. 构建并编译代理

代理使用 StateGraph 类构建，并使用 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

const result = await agent.invoke({
  messages: [new HumanMessage("Add 3 and 4.")],
});

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

恭喜！您已经使用 LangGraph Graph API 构建了您的第一个代理。

Full code example

// Step 1: Define tools and model




const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  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

  StateGraph,
  StateSchema,
  MessagesValue,
  ReducedValue,
  GraphNode,
  ConditionalEdgeRouter,
  START,
  END,
} from "@langchain/langgraph";


const MessagesState = new StateSchema({
  messages: MessagesValue,
  llmCalls: new ReducedValue(
    z.number().default(0),
    { reducer: (x, y) => x + y }
  ),
});

// Step 3: Define model node


const llmCall: GraphNode<typeof MessagesState> = async (state) => {
  return {
    messages: [await modelWithTools.invoke([
      new SystemMessage(
        "You are a helpful assistant tasked with performing arithmetic on a set of inputs."
      ),
      ...state.messages,
    ])],
    llmCalls: 1,
  };
};

// Step 4: Define tool node

const toolNode: GraphNode<typeof MessagesState> = async (state) => {
  const lastMessage = state.messages.at(-1);

  if (lastMessage == null || !AIMessage.isInstance(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


const shouldContinue: ConditionalEdgeRouter<typeof MessagesState, "toolNode"> = (state) => {
  const lastMessage = state.messages.at(-1);

  // Check if it's an AIMessage before accessing tool_calls
  if (!lastMessage || !AIMessage.isInstance(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
const result = await agent.invoke({
  messages: [new HumanMessage("Add 3 and 4.")],
});

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

Use the Functional API

1. 定义工具和模型

在此示例中，我们将使用 Claude Sonnet 4.5 模型，并定义用于加法、乘法和除法的工具。

const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  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。

const callLlm = 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。

const callTool = task({ name: "callTool" }, async (toolCall: ToolCall) => {
  const tool = toolsByName[toolCall.name];
  return tool.invoke(toolCall);
});

4. 定义代理

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


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

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

恭喜！您已经使用 LangGraph 函数式 API 构建了您的第一个代理。

Full code example

  task,
  entrypoint,
  addMessages,
} from "@langchain/langgraph";

  SystemMessage,
  HumanMessage,
  type BaseMessage,
} from "@langchain/core/messages";



// Step 1: Define tools and model

const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  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

const callLlm = 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

const callTool = task({ name: "callTool" }, async (toolCall: ToolCall) => {
  const tool = toolsByName[toolCall.name];
  return tool.invoke(toolCall);
});

// Step 4: Define agent

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

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

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