Skip to main content
Open In ColabOpen on GitHub

ScaNN

ScaNN（可扩展最近邻）是一种用于大规模高效向量相似性搜索的方法。

ScaNN 包含用于最大内积搜索的搜索空间剪枝和量化技术，同时还支持欧几里得距离等其他距离函数。该实现针对支持 AVX2 的 x86 处理器进行了优化。更多详细信息，请参见其 Google Research GitHub。

您需要使用 langchain-community 安装 pip install -qU langchain-community 才能使用此集成

安装​

通过pip安装ScaNN。或者，您也可以按照ScaNN网站上的说明从源码进行安装。

%pip install --upgrade --quiet  scann

检索演示​

以下是展示如何将 ScaNN 与 Huggingface 嵌入结合使用的方法。

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import ScaNN
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)


model_name = "sentence-transformers/all-mpnet-base-v2"
embeddings = HuggingFaceEmbeddings(model_name=model_name)

db = ScaNN.from_documents(docs, embeddings)
query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)

docs[0]

检索QA演示​

接下来，我们演示将 ScaNN 与 Google PaLM API 结合使用。

您可以从https://developers.generativeai.google/tutorials/setup获取API密钥

from langchain.chains import RetrievalQA
from langchain_community.chat_models.google_palm import ChatGooglePalm

palm_client = ChatGooglePalm(google_api_key="YOUR_GOOGLE_PALM_API_KEY")

qa = RetrievalQA.from_chain_type(
    llm=palm_client,
    chain_type="stuff",
    retriever=db.as_retriever(search_kwargs={"k": 10}),
)
print(qa.run("What did the president say about Ketanji Brown Jackson?"))
The president said that Ketanji Brown Jackson is one of our nation's top legal minds, who will continue Justice Breyer's legacy of excellence.
print(qa.run("What did the president say about Michael Phelps?"))
The president did not mention Michael Phelps in his speech.

保存并加载本地检索索引​

db.save_local("/tmp/db", "state_of_union")
restored_db = ScaNN.load_local("/tmp/db", embeddings, index_name="state_of_union")