- 如果你喜欢将代理定义为节点和边的图,请使用 Graph API。
- 如果你喜欢将代理定义为单个函数,请使用 Functional API。
对于此示例,你需要设置一个 Claude (Anthropic) 帐户并获取 API 密钥。然后,在终端中设置
ANTHROPIC_API_KEY 环境变量。- 使用 Graph API
- 使用 Functional API
1. 定义工具和模型
在这个例子中,我们将使用 Claude Sonnet 4.5 模型并定义加法、乘法和除法工具。Copy
import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";
const model = new ChatAnthropic({
model: "claude-sonnet-4-6",
temperature: 0,
});
// 定义工具
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"),
}),
});
// 将工具绑定到 LLM
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 中的状态在代理执行期间持续存在。
MessagesValue 提供了一个内置的 reducer 用于追加消息。llmCalls 字段使用带有 (x, y) => x + y 的 ReducedValue 来累积计数。Copy
import {
StateGraph,
StateSchema,
MessagesValue,
ReducedValue,
GraphNode,
ConditionalEdgeRouter,
START,
END,
} from "@langchain/langgraph";
import { z } from "zod/v4";
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。Copy
import { SystemMessage } from "@langchain/core/messages";
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。Copy
import { AIMessage, ToolMessage } from "@langchain/core/messages";
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 是否进行工具调用来路由到工具节点或结束。Copy
const shouldContinue: ConditionalEdgeRouter<typeof MessagesState, "toolNode"> = (state) => {
const lastMessage = state.messages.at(-1);
// 在访问 tool_calls 之前检查是否为 AIMessage
if (!lastMessage || !AIMessage.isInstance(lastMessage)) {
return END;
}
// 如果 LLM 进行了工具调用,则执行操作
if (lastMessage.tool_calls?.length) {
return "toolNode";
}
// 否则,停止(回复用户)
return END;
};
6. 构建和编译代理
代理使用StateGraph 类构建,并使用 compile 方法编译。Copy
const agent = new StateGraph(MessagesState)
.addNode("llmCall", llmCall)
.addNode("toolNode", toolNode)
.addEdge(START, "llmCall")
.addConditionalEdges("llmCall", shouldContinue, ["toolNode", END])
.addEdge("toolNode", "llmCall")
.compile();
// 调用
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.type}]: ${message.text}`);
}
要了解如何使用 LangSmith 跟踪你的代理,请参阅 LangSmith 文档。
完整代码示例
完整代码示例
Copy
// 第一步:定义工具和模型
import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";
const model = new ChatAnthropic({
model: "claude-sonnet-4-6",
temperature: 0,
});
// 定义工具
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"),
}),
});
// 将工具绑定到 LLM
const toolsByName = {
[add.name]: add,
[multiply.name]: multiply,
[divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);
Copy
// 第二步:定义状态
import {
StateGraph,
StateSchema,
MessagesValue,
ReducedValue,
GraphNode,
ConditionalEdgeRouter,
START,
END,
} from "@langchain/langgraph";
import * as z from "zod";
const MessagesState = new StateSchema({
messages: MessagesValue,
llmCalls: new ReducedValue(
z.number().default(0),
{ reducer: (x, y) => x + y }
),
});
Copy
// 第三步:定义模型节点
import { SystemMessage, AIMessage, ToolMessage } from "@langchain/core/messages";
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,
};
};
// 第四步:定义工具节点
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 };
};
Copy
// 第五步:定义决定是否结束的逻辑
import { ConditionalEdgeRouter, END } from "@langchain/langgraph";
const shouldContinue: ConditionalEdgeRouter<typeof MessagesState, "toolNode"> = (state) => {
const lastMessage = state.messages.at(-1);
// 在访问 tool_calls 之前检查是否为 AIMessage
if (!lastMessage || !AIMessage.isInstance(lastMessage)) {
return END;
}
// 如果 LLM 进行了工具调用,则执行操作
if (lastMessage.tool_calls?.length) {
return "toolNode";
}
// 否则,停止(回复用户)
return END;
};
Copy
// 第六步:构建并编译代理
import { HumanMessage } from "@langchain/core/messages";
import { StateGraph, START, END } from "@langchain/langgraph";
const agent = new StateGraph(MessagesState)
.addNode("llmCall", llmCall)
.addNode("toolNode", toolNode)
.addEdge(START, "llmCall")
.addConditionalEdges("llmCall", shouldContinue, ["toolNode", END])
.addEdge("toolNode", "llmCall")
.compile();
// 调用
const result = await agent.invoke({
messages: [new HumanMessage("Add 3 and 4.")],
});
for (const message of result.messages) {
console.log(`[${message.type}]: ${message.text}`);
}
1. 定义工具和模型
在这个例子中,我们将使用 Claude Sonnet 4.5 模型并定义加法、乘法和除法工具。Copy
import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import * as z from "zod";
const model = new ChatAnthropic({
model: "claude-sonnet-4-6",
temperature: 0,
});
// 定义工具
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"),
}),
});
// 将工具绑定到 LLM
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。Copy
import { task, entrypoint } from "@langchain/langgraph";
import { SystemMessage } from "@langchain/core/messages";
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。Copy
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. 定义代理
Copy
import { addMessages } from "@langchain/langgraph";
import { type BaseMessage } 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;
}
// 执行工具
const toolResults = await Promise.all(
modelResponse.tool_calls.map((toolCall) => callTool(toolCall))
);
messages = addMessages(messages, [modelResponse, ...toolResults]);
modelResponse = await callLlm(messages);
}
return messages;
});
// 调用
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}`);
}
要了解如何使用 LangSmith 跟踪你的代理,请参阅 LangSmith 文档。
完整代码示例
完整代码示例
Copy
import { ChatAnthropic } from "@langchain/anthropic";
import { tool } from "@langchain/core/tools";
import {
task,
entrypoint,
addMessages,
} from "@langchain/langgraph";
import {
SystemMessage,
HumanMessage,
type BaseMessage,
} from "@langchain/core/messages";
import type { ToolCall } from "@langchain/core/messages/tool";
import * as z from "zod";
// 第一步:定义工具和模型
const model = new ChatAnthropic({
model: "claude-sonnet-4-6",
temperature: 0,
});
// 定义工具
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"),
}),
});
// 将工具绑定到 LLM
const toolsByName = {
[add.name]: add,
[multiply.name]: multiply,
[divide.name]: divide,
};
const tools = Object.values(toolsByName);
const modelWithTools = model.bindTools(tools);
// 第二步:定义模型节点
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,
]);
});
// 第三步:定义工具节点
const callTool = task({ name: "callTool" }, async (toolCall: ToolCall) => {
const tool = toolsByName[toolCall.name];
return tool.invoke(toolCall);
});
// 第四步: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;
}
// 执行工具
const toolResults = await Promise.all(
modelResponse.tool_calls.map((toolCall) => callTool(toolCall))
);
messages = addMessages(messages, [modelResponse, ...toolResults]);
modelResponse = await callLlm(messages);
}
return messages;
});
// 调用
const result = await agent.invoke([new HumanMessage("Add 3 and 4.")]);
for (const message of result) {
console.log(`[${message.type}]: ${message.text}`);
}
将这些文档连接 到 Claude、VSCode 等,通过 MCP 获取实时解答。

