LangChain v1 新特性

from langchain.agents import create_agent

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[search_web, analyze_data, send_email],
    system_prompt="You are a helpful research assistant."
)

result = agent.invoke({
    "messages": [
        {"role": "user", "content": "Research AI safety trends"}
    ]
})

from langchain.agents import create_agent
from langchain.agents.middleware import (
    PIIMiddleware,
    SummarizationMiddleware,
    HumanInTheLoopMiddleware
)


agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[read_email, send_email],
    middleware=[
        PIIMiddleware("email", strategy="redact", apply_to_input=True),
        PIIMiddleware(
            "phone_number",
            detector=(
                r"(?:\+?\d{1,3}[\s.-]?)?"
                r"(?:\(?\d{2,4}\)?[\s.-]?)?"
                r"\d{3,4}[\s.-]?\d{4}"
			),
			strategy="block"
        ),
        SummarizationMiddleware(
            model="claude-sonnet-4-6",
            trigger={"tokens": 500}
        ),
        HumanInTheLoopMiddleware(
            interrupt_on={
                "send_email": {
                    "allowed_decisions": ["approve", "edit", "reject"]
                }
            }
        ),
    ]
)

from dataclasses import dataclass
from typing import Callable

from langchain_openai import ChatOpenAI

from langchain.agents.middleware import (
    AgentMiddleware,
    ModelRequest
)
from langchain.agents.middleware.types import ModelResponse

@dataclass
class Context:
    user_expertise: str = "beginner"

class ExpertiseBasedToolMiddleware(AgentMiddleware):
    def wrap_model_call(
        self,
        request: ModelRequest,
        handler: Callable[[ModelRequest], ModelResponse]
    ) -> ModelResponse:
        user_level = request.runtime.context.user_expertise

        if user_level == "expert":
            # 更强大的模型
            model = ChatOpenAI(model="gpt-5.4")
            tools = [advanced_search, data_analysis]
        else:
            # 较弱的模型
            model = ChatOpenAI(model="gpt-5-nano")
            tools = [simple_search, basic_calculator]

        return handler(request.override(model=model, tools=tools))

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=[
        simple_search,
        advanced_search,
        basic_calculator,
        data_analysis
    ],
    middleware=[ExpertiseBasedToolMiddleware()],
    context_schema=Context
)

from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy
from pydantic import BaseModel


class Weather(BaseModel):
    temperature: float
    condition: str

def weather_tool(city: str) -> str:
    """获取城市的天气。"""
    return f"it's sunny and 70 degrees in {city}"

agent = create_agent(
    "gpt-5.4-mini",
    tools=[weather_tool],
    response_format=ToolStrategy(Weather)
)

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

print(repr(result["structured_response"]))
# 结果为 `Weather(temperature=70.0, condition='sunny')`

from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-6")
response = model.invoke("What's the capital of France?")

# 统一访问内容块
for block in response.content_blocks:
    if block["type"] == "reasoning":
        print(f"模型推理: {block['reasoning']}")
    elif block["type"] == "text":
        print(f"响应: {block['text']}")
    elif block["type"] == "tool_call":
        print(f"工具调用: {block['name']}({block['args']})")

# 智能体构建
from langchain.agents import create_agent

# 消息和内容
from langchain.messages import AIMessage, HumanMessage

# 工具
from langchain.tools import tool

# 模型初始化
from langchain.chat_models import init_chat_model
from langchain.embeddings import init_embeddings

from langchain import ...  
from langchain_classic import ...  

from langchain.chains import ...  
from langchain_classic.chains import ...  

from langchain.retrievers import ...  
from langchain_classic.retrievers import ...  

from langchain import hub  
from langchain_classic import hub