这里涉及的不是单次工具，而是多次多个工具，我以为比较有借鉴性，作个录入。

比较好的实践，是需要很好的结合这两者的。

代码

import os

from langchain_core.messages import HumanMessage
from langchain_core.output_parsers import PydanticOutputParser
from pydantic import BaseModel, Field
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool


# 加载环境变量
from dotenv import load_dotenv


load_dotenv()
deepseek_api_key = os.getenv("DEEPSEEK_API_KEY")
llm = ChatOpenAI(
    model_name="deepseek-chat",
    openai_api_key=deepseek_api_key,
    openai_api_base="https://api.deepseek.com/v1",
    temperature=0.3
)

from langgraph.graph import StateGraph, MessagesState, START, END
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool
from langchain_core.prompts import ChatPromptTemplate
from langgraph.prebuilt import ToolNode

# 1. 定义工具（LangChain）
@tool
def calculate(expression: str) -> str:
    """执行数学计算"""
    return str(eval(expression))

tools = [calculate]

# 2. 定义提示词（LangChain）
prompt = ChatPromptTemplate.from_messages([
    ("system", "你是一个数学助手，可以使用计算工具"),
    ("placeholder", "{messages}")
])

# 3. 定义 Agent 节点（LangChain + LangGraph）
def agent(state: MessagesState):
    llm_bind_tools = llm.bind_tools(tools)
    chain = prompt | llm_bind_tools
    response = chain.invoke({"messages": state["messages"]})
    return {"messages": [response]}

# 4. 条件路由（LangGraph）
def should_continue(state: MessagesState):
    last_message = state["messages"][-1]
    if hasattr(last_message, "tool_calls") and last_message.tool_calls:
        return "tools"
    return END

# 5. 构建图（LangGraph）
graph = StateGraph(MessagesState)
graph.add_node("agent", agent)
graph.add_node("tools", ToolNode(tools))

graph.add_edge(START, "agent")
graph.add_conditional_edges("agent", should_continue)
graph.add_edge("tools", "agent")

app = graph.compile()

# 🎨 可视化图结构
from IPython.display import Image, display
display(Image(app.get_graph().draw_mermaid_png()))

# 6. 测试
response = app.invoke({
    "messages": [("user", "计算 (25 + 75) * 2 / 10，再计算(9 / 3) * (5-2)")]
})
print(response["messages"][-1].content)

输出

<IPython.core.display.Image object>
第二个表达式的结果是：9

总结：
1. (25 + 75) × 2 ÷ 10 = 20
2. (9 ÷ 3) × (5 - 2) = 9

进程已结束，退出代码为 0