LangChain 中文文档

外观

智能体 = 模型 + 框架。 LangChain 提供 create_agent：一个极简且高度可配置的框架。框架指的是模型循环之外的一切：提示词、工具，以及任何塑造行为的中间件。从基础原语开始，精确组合出你的用例所需的一切。支持 OpenAI、Anthropic、Google 等。

TIP

LangChain vs. LangGraph vs. Deep Agents

从 Deep Agents 开始，可以获取一个"开箱即用"的智能体，它具备自动上下文压缩、虚拟文件系统和子智能体生成等功能。Deep Agents 基于 LangChain 的 agents 构建，你也可以直接使用这些 agents。

使用 LangChain（create_agent）可以获得一个高度可定制的框架，可以轻松针对你的用例和数据量身定制。

对于结合确定性工作流与智能体工作流的进阶需求，请使用 LangGraph，我们的底层编排框架。

使用 LangSmith 来追踪、调试和评估使用上述任一框架构建的智能体。按照追踪快速入门进行设置。我们还建议你设置 LangSmith Engine，它可以监控你的追踪、检测问题并提出修复方案。

创建智能体 ​

本示例演示如何使用自定义工具创建一个简单的 LangChain 智能体：

python
# pip install -qU langchain "langchain[openai]"
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="openai:gpt-5.5",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain "langchain[google-genai]"
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="google_genai:gemini-2.5-flash-lite",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain "langchain[anthropic]"
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain langchain-openrouter
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="openrouter:anthropic/claude-sonnet-4-6",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain langchain-fireworks
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="fireworks:accounts/fireworks/models/qwen3p5-397b-a17b",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain langchain-baseten
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="baseten:zai-org/GLM-5.2",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain langchain-ollama
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="ollama:devstral-2",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain "langchain[openai]"
import os
from langchain.agents import create_agent
from langchain.chat_models import init_chat_model

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

model = init_chat_model(
    "azure_openai:gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)
agent = create_agent(
    model=model,
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain langchain-aws
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

# US cross-region inference profile; use global.anthropic.claude-sonnet-4-6 for worldwide routing.
agent = create_agent(
    model="bedrock_converse:us.anthropic.claude-sonnet-4-6",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
python
# pip install -qU langchain "langchain[huggingface]"
from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="huggingface:microsoft/Phi-3-mini-4k-instruct",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)
ts
// First install: npm install langchain zod @langchain/openai
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "gpt-5.5",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/google-genai
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "google-genai:gemini-2.5-flash-lite",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/anthropic
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "claude-sonnet-4-6",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/openrouter
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "openrouter:anthropic/claude-sonnet-4-6",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "fireworks:accounts/fireworks/models/qwen3p5-397b-a17b",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "baseten:zai-org/GLM-5.2",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/ollama
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "ollama:devstral-2",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/openai
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "azure_openai:gpt-5.5",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);
ts
// First install: npm install langchain zod @langchain/aws
import { createAgent, tool } from "langchain";
import * as z from "zod";

const getWeather = tool(
  (input) => `It's always sunny in ${input.city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string().describe("The city to get the weather for"),
    }),
  }
);

const agent = createAgent({
  model: "bedrock:gpt-5.5",
  tools: [getWeather],
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
  })
);

查看安装说明和快速入门指南，开始使用 LangChain 构建你自己的智能体和应用程序。

TIP

使用 LangSmith 来追踪请求、调试智能体行为并评估输出。设置 LANGSMITH_TRACING=true 和你的 API 密钥即可开始。

核心优势 ​

  • 标准模型接口 — 跨提供商使用一个统一的接口来处理对话模型、嵌入等。只需对代码做最小改动即可切换模型，并让你的应用程序在需求变化时保持可移植性。

  • 高度可配置的框架 — 从 create_agent 这个极简框架开始，通过中间件增量地添加能力。只组合你的用例所需的部分，从护栏和重试到路由和自定义工具策略。

  • 构建于 LangGraph 之上 — LangChain 的智能体构建于 LangGraph 之上。这使我们能够利用 LangGraph 的持久化执行、人在回路支持、持久化等功能。

  • 使用 LangSmith 调试 — 在一个地方检查追踪、工具调用、状态转换和延迟。借助执行数据发现失败模式、评估质量并改进智能体行为。