跳到主要内容
Open In ColabOpen on GitHub

ScaNN

ScaNN（Scalable Nearest Neighbors）是一种用于高效大规模向量相似性搜索的方法。

ScaNN 包括用于最大内积搜索（Maximum Inner Product Search）的搜索空间剪枝和量化，并且还支持其他距离函数，例如欧几里得距离（Euclidean distance）。该实现针对支持 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 页面。

您需要安装 langchain-community (使用 pip install -qU langchain-community) 才能使用此集成

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安装。

%pip install --upgrade --quiet  scann

检索演示​

下面展示了如何结合 Huggingface Embeddings 使用 ScaNN。

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，我们将演示如何结合 Google PaLM API 使用 ScaNN。

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")