NanoPQ（产品量化）

Product Quantization algorithm (k-NN) in brief is a quantization algorithm that helps in compression of database vectors which helps in semantic search when large datasets are involved. In a nutshell, the embedding is split into M subspaces which further goes through clustering. Upon clustering the vectors the centroid vector gets mapped to the vectors present in the each of the clusters of the subspace.

本笔记本介绍了如何使用一个底层采用产品量化（Product Quantization）的检索器，该功能由nanopq包实现。

%pip install -qU langchain-community langchain-openai nanopq

from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings
from langchain_community.retrievers import NanoPQRetriever

API 参考：SpacyEmbeddings | NanoPQRetriever

使用文本创建新的检索器

retriever = NanoPQRetriever.from_texts(
    ["Great world", "great words", "world", "planets of the world"],
    SpacyEmbeddings(model_name="en_core_web_sm"),
    clusters=2,
    subspace=2,
)

使用检索器

我们现在可以使用检索器了！

retriever.invoke("earth")

M: 2, Ks: 2, metric : <class 'numpy.uint8'>, code_dtype: l2
iter: 20, seed: 123
Training the subspace: 0 / 2
Training the subspace: 1 / 2
Encoding the subspace: 0 / 2
Encoding the subspace: 1 / 2

[Document(page_content='world'),
 Document(page_content='Great world'),
 Document(page_content='great words'),
 Document(page_content='planets of the world')]

相关

• 检索器 概念指南
• 检索器 操操作指南