ScaNN
ScaNN（可扩展最近邻）是一种在大规模数据中进行高效向量相似性搜索的方法。
ScaNN 包含搜索空间修剪和量化，用于最大内积搜索，也支持其他距离函数，如欧氏距离。实现针对支持 AVX2 的 x86 处理器进行了优化。有关更多详细信息，请参阅其 Google Research github。
要使用此集成，您需要使用 pip install -qU langchain-community 安装 langchain-community。
安装
通过 pip 安装 ScaNN。或者，您可以按照 ScaNN 网站 上的说明从源代码进行安装。
%pip install --upgrade --quiet scann
检索演示
下面我们展示如何将 ScaNN 与 Huggingface Embeddings 结合使用。
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]
RetrievalQA 演示
接下来，我们演示如何将 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}),
)
API 参考：RetrievalQA | ChatGooglePalm
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.
保存和加载本地检索索引
db.save_local("/tmp/db", "state_of_union")
restored_db = ScaNN.load_local("/tmp/db", embeddings, index_name="state_of_union")