LangChain create_agent 智能体创建教程 - 构建AI助手与工具集成

langchain-fundamentals by langchain-ai/langchain-skills

2,500 周安装量

423 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/langchain-ai/langchain-skills --skill langchain-fundamentals

AI/机器学习开发

🇨🇳中文介绍

<create_agent>

使用 create_agent 创建智能体

create_agent() 是构建智能体的推荐方法。它负责处理智能体循环、工具执行和状态管理。

智能体配置选项

参数	用途	示例
`model`	使用的 LLM	`"anthropic:claude-sonnet-4-5"` 或模型实例
`tools`	工具列表	`[search, calculator]`
`system_prompt` /

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

733,500 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

252,100 周安装

Vercel Web界面规范检查工具 - 自动检测代码是否符合Web设计指南

202,600 周安装

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

133,200 周安装

</python>
<typescript>
```typescript
import { createAgent } from "langchain";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const getWeather = tool(
  async ({ location }) => `Weather in ${location}: Sunny, 72F`,
  {
    name: "get_weather",
    description: "Get current weather for a location.",
    schema: z.object({ location: z.string().describe("City name") }),
  }
);

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [getWeather],
  systemPrompt: "You are a helpful assistant.",
});

const result = await agent.invoke({
  messages: [{ role: "user", content: "What's the weather in Paris?" }],
});
console.log(result.messages[result.messages.length - 1].content);

</python>
<typescript>
添加 MemorySaver 检查点以在多次调用间维持对话状态。
```typescript
import { createAgent } from "langchain";
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [search],
  checkpointer,
});

const config = { configurable: { thread_id: "user-123" } };
await agent.invoke({ messages: [{ role: "user", content: "My name is Alice" }] }, config);
const result = await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] }, config);
// Agent remembers: "Your name is Alice"

Args:
    a: 第一个数字
    b: 第二个数字
"""
return a + b



</python>
<typescript>
```typescript
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const add = tool(
  async ({ 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"),
    }),
  }
);

中间件可以拦截智能体循环，以添加人工审批、错误处理、日志记录等功能。深入理解中间件对于生产环境中的智能体至关重要——使用 HumanInTheLoopMiddleware (Python) / humanInTheLoopMiddleware (TypeScript) 来处理审批工作流，使用 @wrap_tool_call (Python) / createMiddleware (TypeScript) 来创建自定义钩子。

人机交互 (HITL) : middleware=[HumanInTheLoopMiddleware(interrupt_on={"dangerous_tool": True})] — 需要 checkpointer + thread_id
中断后恢复 : agent.invoke(Command(resume={"decisions": [{"type": "approve"}]}), config=config)
自定义中间件 : @wrap_tool_call 装饰器 (Python) 或 createMiddleware({ wrapToolCall: ... }) (TypeScript)

</python>
<typescript>
```typescript
import { ChatOpenAI } from "@langchain/openai";
import { z } from "zod";

const ContactInfo = z.object({
  name: z.string(),
  email: z.string().email(),
  phone: z.string().describe("Phone number with area code"),
});

// 模型级别的结构化输出
const model = new ChatOpenAI({ model: "gpt-4.1" });
const structuredModel = model.withStructuredOutput(ContactInfo);
const response = await structuredModel.invoke("Extract: John, john@example.com, 555-1234");
// { name: 'John', email: 'john@example.com', phone: '555-1234' }

当你需要最新数据或事实时使用此工具。

Args:
    query: 搜索查询（建议 2-10 个单词）
"""
return web_search(query)



</python>
<typescript>
清晰的描述有助于智能体了解何时使用每个工具。
```typescript
// 错误示例：模糊的描述
const badTool = tool(async ({ input }) => "result", {
  name: "bad_tool",
  description: "Does stuff.", // 太模糊了！
  schema: z.object({ input: z.string() }),
});

// 正确示例：清晰、具体的描述
const search = tool(async ({ query }) => webSearch(query), {
  name: "search",
  description: "Search the web for current information about a topic. Use this when you need recent data or facts.",
  schema: z.object({
    query: z.string().describe("The search query (2-10 words recommended)"),
  }),
});

</python>
<typescript>
添加检查点和 thread_id 以在多次调用间实现对话记忆。
```typescript
// 错误示例：无持久化
const agent = createAgent({ model: "anthropic:claude-sonnet-4-5", tools: [search] });
await agent.invoke({ messages: [{ role: "user", content: "I'm Bob" }] });
await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] });
// Agent doesn't remember!

// 正确示例：添加检查点和 thread_id
import { MemorySaver } from "@langchain/langgraph";

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [search],
  checkpointer: new MemorySaver(),
});
const config = { configurable: { thread_id: "session-1" } };
await agent.invoke({ messages: [{ role: "user", content: "I'm Bob" }] }, config);
await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] }, config);
// Agent remembers: "Your name is Bob"

</python>
<typescript>
在调用配置中设置 recursionLimit 以防止智能体循环失控。
```typescript
// 错误示例：无迭代限制
const result = await agent.invoke({ messages: [["user", "Do research"]] });

// 正确示例：在配置中设置 recursionLimit
const result = await agent.invoke(
  { messages: [["user", "Do research"]] },
  { recursionLimit: 10 }, // 在 10 步后停止
);

</python>
<typescript>
从结果对象中访问消息数组，而不是直接访问 result.content。
```typescript
// 错误示例：尝试直接访问 result.content
const result = await agent.invoke({ messages: [{ role: "user", content: "Hello" }] });
console.log(result.content); // undefined!

// 正确示例：从结果对象中访问消息
const result = await agent.invoke({ messages: [{ role: "user", content: "Hello" }] });
console.log(result.messages[result.messages.length - 1].content); // 最后一条消息的内容

🇺🇸English

<create_agent>

Creating Agents with create_agent

create_agent() is the recommended way to build agents. It handles the agent loop, tool execution, and state management.

Agent Configuration Options

Parameter	Purpose	Example
`model`	LLM to use	`"anthropic:claude-sonnet-4-5"` or model instance
`tools`	List of tools	`[search, calculator]`
`system_prompt` / `systemPrompt`	Agent instructions	`"You are a helpful assistant"`
`checkpointer`	State persistence	`MemorySaver()`
`middleware`	Processing hooks	`[HumanInTheLoopMiddleware]` (Python) / `[humanInTheLoopMiddleware({...})]` (TypeScript)
</create_agent>

@tool def get_weather(location: str) -> str: """Get current weather for a location.

Args:
    location: City name
"""
return f"Weather in {location}: Sunny, 72F"

agent = create_agent( model="anthropic:claude-sonnet-4-5", tools=[get_weather], system_prompt="You are a helpful assistant." )

result = agent.invoke({ "messages": [{"role": "user", "content": "What's the weather in Paris?"}] }) print(result["messages"][-1].content)

</python>
<typescript>
```typescript
import { createAgent } from "langchain";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const getWeather = tool(
  async ({ location }) => `Weather in ${location}: Sunny, 72F`,
  {
    name: "get_weather",
    description: "Get current weather for a location.",
    schema: z.object({ location: z.string().describe("City name") }),
  }
);

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [getWeather],
  systemPrompt: "You are a helpful assistant.",
});

const result = await agent.invoke({
  messages: [{ role: "user", content: "What's the weather in Paris?" }],
});
console.log(result.messages[result.messages.length - 1].content);

checkpointer = MemorySaver()

agent = create_agent( model="anthropic:claude-sonnet-4-5", tools=[search], checkpointer=checkpointer, )

config = {"configurable": {"thread_id": "user-123"}} agent.invoke({"messages": [{"role": "user", "content": "My name is Alice"}]}, config=config) result = agent.invoke({"messages": [{"role": "user", "content": "What's my name?"}]}, config=config)

Agent remembers: "Your name is Alice"

</python>
<typescript>
Add MemorySaver checkpointer to maintain conversation state across invocations.
```typescript
import { createAgent } from "langchain";
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [search],
  checkpointer,
});

const config = { configurable: { thread_id: "user-123" } };
await agent.invoke({ messages: [{ role: "user", content: "My name is Alice" }] }, config);
const result = await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] }, config);
// Agent remembers: "Your name is Alice"

Tools are functions that agents can call. Use the @tool decorator (Python) or tool() function (TypeScript).

@tool def add(a: float, b: float) -> float: """Add two numbers.

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



</python>
<typescript>
```typescript
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const add = tool(
  async ({ 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"),
    }),
  }
);

Middleware intercepts the agent loop to add human approval, error handling, logging, and more. A deep understanding of middleware is essential for production agents — use HumanInTheLoopMiddleware (Python) / humanInTheLoopMiddleware (TypeScript) for approval workflows, and @wrap_tool_call (Python) / createMiddleware (TypeScript) for custom hooks.

Key imports:

from langchain.agents.middleware import HumanInTheLoopMiddleware, wrap_tool_call



import { humanInTheLoopMiddleware, createMiddleware } from "langchain";

Key patterns:

HITL : middleware=[HumanInTheLoopMiddleware(interrupt_on={"dangerous_tool": True})] — requires checkpointer + thread_id
Resume after interrupt : agent.invoke(Command(resume={"decisions": [{"type": "approve"}]}), config=config)
Custom middleware : @wrap_tool_call decorator (Python) or createMiddleware({ wrapToolCall: ... }) (TypeScript)

<structured_output>

Structured Output

Get typed, validated responses from agents using response_format or with_structured_output().

class ContactInfo(BaseModel): name: str email: str phone: str = Field(description="Phone number with area code")

Option 1: Agent with structured output

agent = create_agent(model="gpt-4.1", tools=[search], response_format=ContactInfo) result = agent.invoke({"messages": [{"role": "user", "content": "Find contact for John"}]}) print(result["structured_response"]) # ContactInfo(name='John', ...)

Option 2: Model-level structured output (no agent needed)

from langchain_openai import ChatOpenAI model = ChatOpenAI(model="gpt-4.1") structured_model = model.with_structured_output(ContactInfo) response = structured_model.invoke("Extract: John, john@example.com, 555-1234")

ContactInfo(name='John', email='john@example.com', phone='555-1234')

</python>
<typescript>
```typescript
import { ChatOpenAI } from "@langchain/openai";
import { z } from "zod";

const ContactInfo = z.object({
  name: z.string(),
  email: z.string().email(),
  phone: z.string().describe("Phone number with area code"),
});

// Model-level structured output
const model = new ChatOpenAI({ model: "gpt-4.1" });
const structuredModel = model.withStructuredOutput(ContactInfo);
const response = await structuredModel.invoke("Extract: John, john@example.com, 555-1234");
// { name: 'John', email: 'john@example.com', phone: '555-1234' }

<model_config>

Model Configuration

create_agent accepts model strings ("anthropic:claude-sonnet-4-5", "openai:gpt-4.1") or model instances for custom settings:

from langchain_anthropic import ChatAnthropic
agent = create_agent(model=ChatAnthropic(model="claude-sonnet-4-5", temperature=0), tools=[...])

</model_config>

CORRECT: Clear, specific description with Args

@tool def search(query: str) -> str: """Search the web for current information about a topic.

Use this when you need recent data or facts.

Args:
    query: The search query (2-10 words recommended)
"""
return web_search(query)



</python>
<typescript>
Clear descriptions help the agent know when to use each tool.
```typescript
// WRONG: Vague description
const badTool = tool(async ({ input }) => "result", {
  name: "bad_tool",
  description: "Does stuff.", // Too vague!
  schema: z.object({ input: z.string() }),
});

// CORRECT: Clear, specific description
const search = tool(async ({ query }) => webSearch(query), {
  name: "search",
  description: "Search the web for current information about a topic. Use this when you need recent data or facts.",
  schema: z.object({
    query: z.string().describe("The search query (2-10 words recommended)"),
  }),
});

CORRECT: Add checkpointer and thread_id

from langgraph.checkpoint.memory import MemorySaver

agent = create_agent( model="anthropic:claude-sonnet-4-5", tools=[search], checkpointer=MemorySaver(), ) config = {"configurable": {"thread_id": "session-1"}} agent.invoke({"messages": [{"role": "user", "content": "I'm Bob"}]}, config=config) agent.invoke({"messages": [{"role": "user", "content": "What's my name?"}]}, config=config)

Agent remembers: "Your name is Bob"

</python>
<typescript>
Add checkpointer and thread_id for conversation memory across invocations.
```typescript
// WRONG: No persistence
const agent = createAgent({ model: "anthropic:claude-sonnet-4-5", tools: [search] });
await agent.invoke({ messages: [{ role: "user", content: "I'm Bob" }] });
await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] });
// Agent doesn't remember!

// CORRECT: Add checkpointer and thread_id
import { MemorySaver } from "@langchain/langgraph";

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-5",
  tools: [search],
  checkpointer: new MemorySaver(),
});
const config = { configurable: { thread_id: "session-1" } };
await agent.invoke({ messages: [{ role: "user", content: "I'm Bob" }] }, config);
await agent.invoke({ messages: [{ role: "user", content: "What's my name?" }] }, config);
// Agent remembers: "Your name is Bob"

CORRECT: Set recursion_limit in config

result = agent.invoke( {"messages": [("user", "Do research")]}, config={"recursion_limit": 10}, # Stop after 10 steps )

</python>
<typescript>
Set recursionLimit in the invoke config to prevent runaway agent loops.
```typescript
// WRONG: No iteration limit
const result = await agent.invoke({ messages: [["user", "Do research"]] });

// CORRECT: Set recursionLimit in config
const result = await agent.invoke(
  { messages: [["user", "Do research"]] },
  { recursionLimit: 10 }, // Stop after 10 steps
);

CORRECT: Access messages from result dict

result = agent.invoke({"messages": [{"role": "user", "content": "Hello"}]}) print(result["messages"][-1].content) # Last message content

</python>
<typescript>
Access the messages array from the result, not result.content directly.
```typescript
// WRONG: Trying to access result.content directly
const result = await agent.invoke({ messages: [{ role: "user", content: "Hello" }] });
console.log(result.content); // undefined!

// CORRECT: Access messages from result object
const result = await agent.invoke({ messages: [{ role: "user", content: "Hello" }] });
console.log(result.messages[result.messages.length - 1].content); // Last message content

Weekly Installs

2.5K

Repository

langchain-ai/la…n-skills

GitHub Stars

423

First Seen

Feb 21, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

claude-code2.0K

codex2.0K

cursor2.0K

github-copilot1.9K

opencode1.9K

gemini-cli1.9K

LangChain create_agent 智能体创建教程 - 构建AI助手与工具集成

🇨🇳中文介绍

使用 create_agent 创建智能体

智能体配置选项

相关 Skills

Agent remembers: "Your name is Alice"

结构化输出

选项 1: 具有结构化输出的智能体

选项 2: 模型级别的结构化输出（无需智能体）

ContactInfo(name='John', email='john@example.com', phone='555-1234')

模型配置

正确示例：清晰、具体的描述，包含 Args

正确示例：添加检查点和 thread_id

Agent remembers: "Your name is Bob"

正确示例：在配置中设置 recursion_limit

正确示例：从结果字典中访问消息

🇺🇸English

Creating Agents with create_agent

Agent Configuration Options

Agent remembers: "Your name is Alice"

Structured Output

Option 1: Agent with structured output

Option 2: Model-level structured output (no agent needed)

ContactInfo(name='John', email='john@example.com', phone='555-1234')

Model Configuration

CORRECT: Clear, specific description with Args

CORRECT: Add checkpointer and thread_id

Agent remembers: "Your name is Bob"

CORRECT: Set recursion_limit in config

CORRECT: Access messages from result dict

最新 Skills