AI大模型应用开发-用LangChain构建带Agen流程的RAG系统

技术分享 9个月前 (06-18) 0 999+

随着大模型（LLM）能力越来越强，RAG（Retrieval Augmented Generation，检索增强生成）技术成为增强大模型知识准确性的关键手段。

通过检索实时数据、外部文档，模型能回答更多基于事实的问题，降低“幻觉”概率。

而 LangChain 的 LangGraph 能将 LLM、RAG、工具调用（Tools）整合成一个智能 Agent 流程图，极大提升了问答系统的动态能力。

本文通过一个完整示例，展示如何用 LangChain 构建一个「RAG + Agent」的问答系统，代码可直接复用，帮助大家快速落地智能应用。

工程结构

llm_env.py          # 初始化 LLM rag_agent.py        # 结合 RAG 与 Agent 的主逻辑

初始化 LLM

首先通过 llm_env.py 初始化一个 LLM 模型对象，供整个流程使用：

from langchain.chat_models import init_chat_model  llm = init_chat_model("gpt-4o-mini", model_provider="openai")

RAG + Agent 系统搭建

导入依赖

import os import sys import time  sys.path.append(os.getcwd())  from llm_set import llm_env from langchain.embeddings import OpenAIEmbeddings from langchain_postgres import PGVector from langchain_community.document_loaders import WebBaseLoader from langchain_core.documents import Document from langchain_text_splitters import RecursiveCharacterTextSplitter from langgraph.graph import MessagesState, StateGraph from langchain_core.tools import tool from langchain_core.messages import HumanMessage, SystemMessage from langgraph.prebuilt import ToolNode, tools_condition from langgraph.graph import END from langgraph.checkpoint.postgres import PostgresSaver

初始化 LLM 与 Embedding

llm = llm_env.llm  embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

初始化向量数据库

vector_store = PGVector(     embeddings=embeddings,     collection_name="my_rag_agent_docs",     connection="postgresql+psycopg2://postgres:123456@localhost:5433/langchainvector", )

加载网页文档

url = "https://www.cnblogs.com/chenyishi/p/18926783" loader = WebBaseLoader(     web_paths=(url,), ) docs = loader.load() for doc in docs:     doc.metadata["source"] = url

文本分割 & 入库

text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=50) all_splits = text_splitter.split_documents(docs)  existing = vector_store.similarity_search(url, k=1, filter={"source": url}) if not existing:     _ = vector_store.add_documents(documents=all_splits)     print("文档向量化完成")

定义 RAG 检索工具

通过 @tool 装饰器，定义一个文档检索工具，供 Agent 动态调用：

@tool(response_format="content_and_artifact") def retrieve(query: str) -> tuple[str, dict]:     """Retrieve relevant documents from the vector store."""     retrieved_docs = vector_store.similarity_search(query, k=2)     if not retrieved_docs:         return "No relevant documents found.", {}     return "nn".join(         (f"Source: {doc.metadata}n" f"Content: {doc.page_content}")         for doc in retrieved_docs     ), retrieved_docs

定义 Agent Graph 节点

LLM 调用工具节点

def query_or_respond(state: MessagesState):     llm_with_tools = llm.bind_tools([retrieve])     response = llm_with_tools.invoke(state["messages"])     return {"messages": [response]}

工具节点

tools = ToolNode([retrieve])

生成响应节点

def generate(state: MessagesState):     recent_tool_messages = []     for message in reversed(state["messages"]):         if message.type == "tool":             recent_tool_messages.append(message)         else:             break      tool_messages = recent_tool_messages[::-1]      system_message_content = "nn".join(doc.content for doc in tool_messages)      conversation_messages = [         message         for message in state["messages"]         if message.type in ("human", "system")         or (message.type == "ai" and not message.tool_calls)     ]     prompt = [SystemMessage(system_message_content)] + conversation_messages      response = llm.invoke(prompt)     return {"messages": [response]}

组装 Agent 流程图

graph_builder = StateGraph(MessagesState) graph_builder.add_node(query_or_respond) graph_builder.add_node(tools) graph_builder.add_node(generate)  graph_builder.set_entry_point("query_or_respond") graph_builder.add_conditional_edges(     "query_or_respond",     tools_condition,     path_map={END: END, "tools": "tools"}, ) graph_builder.add_edge("tools", "generate") graph_builder.add_edge("generate", END)

启用 Checkpoint & 运行流程

数据库存储器

DB_URI = "postgresql://postgres:123456@localhost:5433/langchaindemo?sslmode=disable"  with PostgresSaver.from_conn_string(DB_URI) as checkpointer:     checkpointer.setup()      graph = graph_builder.compile(checkpointer=checkpointer)

启动交互循环

input_thread_id = input("输入thread_id:") time_str = time.strftime("%Y%m%d", time.localtime()) config = {"configurable": {"thread_id": f"rag-{time_str}-demo-{input_thread_id}"}}  print("输入问题，输入 exit 退出。") while True:     query = input("你: ")     if query.strip().lower() == "exit":         break     response = graph.invoke({"messages": [HumanMessage(content=query)]}, config=config)     print(response)