通过阿里云 Milvus 和 LangChain 快速构建 LLM 问答系统

pip3 install pymilvus langchain dashscope beautifulsoup4

vim milvusr-llm.py

from langchain_community.document_loaders import WebBaseLoaderfrom langchain.text_splitter import RecursiveCharacterTextSplitterfrom langchain.vectorstores.milvus import Milvusfrom langchain.schema.runnable import RunnablePassthroughfrom langchain.prompts import PromptTemplatefrom langchain_community.embeddings import DashScopeEmbeddingsfrom langchain_community.llms.pai_eas_endpoint import PaiEasEndpoint
# 设置Milvus Collection名称。COLLECTION_NAME = 'doc_qa_db'
# 设置向量维度。DIMENSION = 768
loader = WebBaseLoader([    'https://milvus.io/docs/overview.md',    'https://milvus.io/docs/release_notes.md',    'https://milvus.io/docs/architecture_overview.md',    'https://milvus.io/docs/four_layers.md',    'https://milvus.io/docs/main_components.md',    'https://milvus.io/docs/data_processing.md',    'https://milvus.io/docs/bitset.md',    'https://milvus.io/docs/boolean.md',    'https://milvus.io/docs/consistency.md',    'https://milvus.io/docs/coordinator_ha.md',    'https://milvus.io/docs/replica.md',    'https://milvus.io/docs/knowhere.md',    'https://milvus.io/docs/schema.md',    'https://milvus.io/docs/dynamic_schema.md',    'https://milvus.io/docs/json_data_type.md',    'https://milvus.io/docs/metric.md',    'https://milvus.io/docs/partition_key.md',    'https://milvus.io/docs/multi_tenancy.md',    'https://milvus.io/docs/timestamp.md',    'https://milvus.io/docs/users_and_roles.md',    'https://milvus.io/docs/index.md',    'https://milvus.io/docs/disk_index.md',    'https://milvus.io/docs/scalar_index.md',    'https://milvus.io/docs/performance_faq.md',    'https://milvus.io/docs/product_faq.md',    'https://milvus.io/docs/operational_faq.md',    'https://milvus.io/docs/troubleshooting.md',])
docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=0)
# 使用LangChain将输入文档安照chunk_size切分all_splits = text_splitter.split_documents(docs)
# 设置embedding模型为DashScope（可以替换成自己模型）。
embeddings = DashScopeEmbeddings(    model="text-embedding-v2", dashscope_api_key="your_api_key")
# 创建connection，host为阿里云Milvus的访问域名。
connection_args = {"host": "c-xxxx.milvus.aliyuncs.com", "port": "19530", "user": "your_user", "password": "your_password"}# 创建Collectionvector_store = Milvus(    embedding_function=embeddings,    connection_args=connection_args,    collection_name=COLLECTION_NAME,    drop_old=True,).from_documents(    all_splits,    embedding=embeddings,    collection_name=COLLECTION_NAME,    connection_args=connection_args,)
# 利用Milvus向量数据库进行相似性检索。
query = "What are the main components of Milvus?"docs = vector_store.similarity_search(query)print(len(docs))
# 声明LLM 模型为PAI EAS（可以替换成自己模型）。
llm = PaiEasEndpoint(    eas_service_url="your_pai_eas_url",    eas_service_token="your_token",)
# 将上述相似性检索的结果作为retriever，提出问题输入到LLM之后，获取检索增强之后的回答。
retriever = vector_store.as_retriever()
template = """Use the following pieces of context to answer the question at the end.If you don't know the answer, just say that you don't know, don't try to make up an answer.Use three sentences maximum and keep the answer as concise as possible.Always say "thanks for asking!" at the end of the answer.{context}Question: {question}Helpful Answer:"""rag_prompt = PromptTemplate.from_template(template)
rag_chain = (    {"context": retriever, "question": RunnablePassthrough()}    | rag_prompt    | llm)
print(rag_chain.invoke("Explain IVF_FLAT in Milvus."))

python3 milvusr-llm.py

4IVF_FLAT is a type of index in Milvus that divides vector data into nlist cluster units and compares distances between the target input vector and the center of each cluster. It uses a smaller number of clusters than IVF_FLAT, which means it may have slightly higher query time but also requires less memory. The encoded data stored in each unit is consistent with the original data.