rag pipeline

5 min RAG quickstart

# pip install langchain langchain-openai chromadb
from langchain_community.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA

# 1. 加载文档
loader = TextLoader("my_doc.txt")
docs = loader.load()

# 2. 切块
splitter = RecursiveCharacterTextSplitter(
    chunk_size=500, chunk_overlap=50
)
chunks = splitter.split_documents(docs)

# 3. 向量化 + 存储
db = Chroma.from_documents(chunks, OpenAIEmbeddings())

# 4. 检索 + 生成
qa = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-4o-mini"),
    retriever=db.as_retriever(search_kwargs={"k": 3})
)
print(qa.invoke("文档里说了什么？"))