基于开源大模型的RAG知识库系统搭建完整教程

pip install langchain langchain-community chromadb
pip install sentence-transformers  # 嵌入模型
pip install ollama                 # 本地推理

# 拉取嵌入模型
ollama pull nomic-embed-text

# 拉取DeepSeek-R1作为回答模型
ollama pull deepseek-r1:7b

from langchain_community.embeddings import OllamaEmbeddings
from langchain_community.llms import Ollama
from langchain_community.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import DirectoryLoader
from langchain.chains import RetrievalQA

# 1. 加载文档
loader = DirectoryLoader("./docs/", glob="**/*.md")
documents = loader.load()

# 2. 分割文档
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separators=["

", "
", "。", "！", "？", " ", ""]
)
chunks = text_splitter.split_documents(documents)

# 3. 创建向量库
embeddings = OllamaEmbeddings(model="nomic-embed-text")
vectorstore = Chroma.from_documents(
    documents=chunks,
    embedding=embeddings,
    persist_directory="./chroma_db"
)

# 4. 创建RAG问答链
llm = Ollama(model="deepseek-r1:7b", temperature=0.3)
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(search_kwargs={"k": 4})
)

# 5. 提问
result = qa_chain.run("DeepSeek-R1支持哪些量化版本？")
print(result)