【LLM开发学习三---LangGraph】

Langgraph 构建聊天机器人

import os
from typing import Annotated
from langchain_openai import ChatOpenAI
from typing_extensions import TypedDictfrom langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messagesos.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_PROJECT"]="LangchainDemo4"
os.environ["LANGCHAIN_API_KEY"] = "***"#定义状态
class State(TypedDict):messages: Annotated[list, add_messages] #将messages信息以追加的形式进行更新，不会被覆盖，汇总输出graph_builder = StateGraph(State)#创建图对象llm = ChatOpenAI(api_key='****',base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",model="qwen-plus-2025-04-28"
)#节点类
def chatbot(state: State):#传入llm问题并将输出追加到state['messages']return {"messages": [llm.invoke(state["messages"])]}# The first argument is the unique node name
# The second argument is the function or object that will be called whenever
# the node is used.
graph_builder.add_node("chatbot", chatbot)#添加节点##定义起始边-结束边
graph_builder.add_edge(START, "chatbot")
graph_builder.add_edge("chatbot", END)
graph = graph_builder.compile()#编译def stream_graph_updates(user_input: str):for event in graph.stream({"messages": [{"role": "user", "content": user_input}]}):print(event)#chatbot节点的输出for value in event.values():print("Assistant:", value["messages"][-1].content)#最新信息while True:try:user_input = input("User: ")#持续输入问题if user_input.lower() in ["quit", "exit", "q"]:#如果想要推出print("Goodbye!")breakstream_graph_updates(user_input)except:#出错时，自行询问并停止# fallback if input() is not availableuser_input = "What do you know about LangGraph?"print("User: " + user_input)stream_graph_updates(user_input)break