SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslangchain-use

langchain-use

Agents & models

View repository

Updated 10-16 06:50

About this skill

LangChain Use Skill

LangChain is an open-source framework for building LLM-powered agents and applications.

Installation

Install LangChain using uv (recommended, requires Python 3.10+):

# 安装核心包
uv add langchain

# 安装模型提供商集成
uv add langchain-anthropic  # Anthropic/Claude
uv add langchain-openai     # OpenAI

Quick Reference

Core Workflow

用户查询 -> create_agent() -> ReAct 循环 -> Tool 调用 -> 返回结果

Create an Agent

See Agent Basics

from langchain.agents import create_agent

agent = create_agent(
    model="claude-sonnet-4-5-20250929",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

# 运行 agent
result = agent.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)

Define a Tool

See Tool Basics

from langchain.tools import tool

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

Access Runtime Context

Use ToolRuntime to access state, context, store:

from langchain.tools import tool, ToolRuntime
from dataclasses import dataclass

@dataclass
class Context:
    user_id: str

@tool
def get_user_location(runtime: ToolRuntime[Context]) -> str:
    """Retrieve user location based on user ID."""
    user_id = runtime.context.user_id
    return "Florida" if user_id == "1" else "SF"

Manage Memory

See Short-term Memory See Long-term Memory

from langgraph.checkpoint.memory import InMemorySaver

agent = create_agent(
    model,
    tools,
    checkpointer=InMemorySaver(),  # 短期记忆
)

# 使用 thread_id 维护会话
config = {"configurable": {"thread_id": "1"}}
agent.invoke({"messages": [...]}, config)

Add Middleware

See Middleware Overview

from langchain.agents.middleware import before_model, after_model

@before_model
def trim_messages(state, runtime):
    # 消息修剪逻辑
    return None

Advanced Topics

Topic Documentation Description
Streaming Streaming Real-time output streaming updates
Structured Output Structured Output Pydantic/dataclass output format
Runtime Runtime ToolRuntime and context access
Guardrails Guardrails PII detection, content filtering
MCP MCP Model Context Protocol integration

Integration Topics

Topic Documentation Description
Models Models Multi-provider model initialization
Messages Messages Message types and content blocks
Retrieval Retrieval RAG and knowledge base construction

Key Concepts

Agent

The core abstraction of LangChain 1.0, built on LangGraph. Use create_agent() to create.

Tool

Use the @tool decorator to define. Optional ToolRuntime to access state, context, and store.

Memory

  • Checkpointer: Short-term session memory (InMemorySaver, PostgresSaver)
  • Store: Long-term persistent storage (InMemoryStore)

Middleware

Decorator-style extension mechanism:

  • @before_model - Pre-model call processing
  • @after_model - Post-model call processing
  • @wrap_tool_call - Tool call wrapping
  • @dynamic_prompt - Dynamic system prompt

Common Patterns

Basic Agent

from langchain.agents import create_agent

agent = create_agent(
    model="claude-sonnet-4-5-20250929",
    tools=[my_tool],
    system_prompt="You are helpful.",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "hello"}]}
)

Agent with Memory (session persistence)

from langgraph.checkpoint.memory import InMemorySaver

agent = create_agent(
    model="claude-sonnet-4-5-20250929",
    tools=[my_tool],
    checkpointer=InMemorySaver(),
)

# 使用 thread_id 标识会话
config = {"configurable": {"thread_id": "1"}}
agent.invoke(
    {"messages": [{"role": "user", "content": "My name is Bob"}]},
    config
)
agent.invoke(
    {"messages": [{"role": "user", "content": "What's my name?"}]},
    config
)

Production Memory (using a database)

from langgraph.checkpoint.postgres import PostgresSaver

DB_URI = "postgresql://postgres:postgres@localhost:5432/postgres"
with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
    checkpointer.setup()  # 自动创建表
    agent = create_agent(
        model="claude-sonnet-4-5-20250929",
        tools=[my_tool],
        checkpointer=checkpointer,
    )

Agent with Context (Runtime Context)

from dataclasses import dataclass
from langchain.tools import tool, ToolRuntime

@dataclass
class Context:
    user_id: str

@tool
def get_user_info(runtime: ToolRuntime[Context]) -> str:
    """Get user information."""
    user_id = runtime.context.user_id
    return f"User ID: {user_id}"

agent = create_agent(
    model="claude-sonnet-4-5-20250929",
    tools=[get_user_info],
    context_schema=Context,
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "get my info"}]},
    context=Context(user_id="user_123")
)

Agent with Structured Output

from dataclasses import dataclass
from langchain.agents.structured_output import ToolStrategy

@dataclass
class Response:
    answer: str
    confidence: float

agent = create_agent(
    model="claude-sonnet-4-5-20250929",
    tools=[my_tool],
    response_format=ToolStrategy(Response),
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "what is 2+2?"}]}
)
print(result['structured_response'])
# Response(answer="4", confidence=1.0)

Complete Example (production-grade Agent)

from dataclasses import dataclass
from langchain.agents import create_agent
from langchain.chat_models import init_chat_model
from langchain.tools import tool, ToolRuntime
from langgraph.checkpoint.memory import InMemorySaver
from langchain.agents.structured_output import ToolStrategy

@dataclass
class Context:
    user_id: str

@dataclass
class ResponseFormat:
    answer: str
    confidence: float | None = None

@tool
def get_weather(city: str) -> str:
    """Get weather for a city."""
    return f"Sunny in {city}"

@tool
def get_user_location(runtime: ToolRuntime[Context]) -> str:
    """Get user's location."""
    return "San Francisco" if runtime.context.user_id == "1" else "Unknown"

# 配置模型
model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    temperature=0.5,
    max_tokens=1000
)

# 创建 agent
agent = create_agent(
    model=model,
    system_prompt="You are a weather assistant.",
    tools=[get_weather, get_user_location],
    context_schema=Context,
    response_format=ToolStrategy(ResponseFormat),
    checkpointer=InMemorySaver(),
)

# 运行 agent
config = {"configurable": {"thread_id": "1"}}
result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather?"}]},
    config=config,
    context=Context(user_id="1")
)

Resource Links