---
title: ScaNN
---

ScaNN (Scalable Nearest Neighbors)은 대규모 벡터 유사도 검색을 효율적으로 수행하는 방법입니다.

ScaNN은 Maximum Inner Product Search를 위한 검색 공간 가지치기(pruning)와 양자화(quantization)를 포함하며, Euclidean distance와 같은 다른 거리 함수도 지원합니다. 구현은 AVX2를 지원하는 x86 프로세서에 최적화되어 있습니다. 자세한 내용은 [Google Research github](https://github.com/google-research/google-research/tree/master/scann)를 참조하세요.

이 integration을 사용하려면 `pip install -qU langchain-community`로 `langchain-community`를 설치해야 합니다.

## Installation

pip를 통해 ScaNN을 설치합니다. 또는 [ScaNN Website](https://github.com/google-research/google-research/tree/master/scann#building-from-source)의 지침에 따라 소스에서 설치할 수 있습니다.

```python
pip install -qU  scann

​
Retrieval Demo

아래에서는 Huggingface Embeddings와 함께 ScaNN을 사용하는 방법을 보여줍니다. 
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 Demo

다음으로, Google PaLM API와 함께 ScaNN을 사용하는 방법을 시연합니다. API key는 developers.generativeai.google/tutorials/setup에서 얻을 수 있습니다. 
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.

​
로컬 retrieval index 저장 및 로드

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


---

<Callout icon="pen-to-square" iconType="regular">
    [Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/vectorstores/scann.mdx)
</Callout>
<Tip icon="terminal" iconType="regular">
    [Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for    real-time answers.
</Tip>
⌘I