• Home
  • Categories
  • Tags
  • Pricing
  • Submit
  1. Home
  2. Sdks & Libraries
  3. Product-Quantization

Product-Quantization

Product-Quantization is a GitHub repository implementing the inverted multi-index structure for product-quantization-based approximate nearest neighbor search, providing building blocks for scalable vector search engines.

🌐Visit Website

About this tool

Product-Quantization

Category: SDKs & Libraries
Slug: product-quantization
Source: https://github.com/jatin7gupta/Product-Quantization

Overview

Product-Quantization is a Python-based implementation of product quantization (PQ) for approximate nearest neighbor (ANN) search, combined with an inverted multi-index structure. It targets scalable vector search on high-dimensional data, such as SIFT and GIST descriptors.

Features

  • Product Quantization for n-dimensional data

    • Decomposes the original vector space into a Cartesian product of multiple low-dimensional subspaces.
    • Quantizes each subspace separately to generate compact codes.
    • Represents each vector as a short code made from subspace quantization indices.
  • Approximate Distance Computation

    • Efficient estimation of L1 (Manhattan) distance between vectors using their PQ codes.
    • Supports an asymmetric distance computation variant (vector-to-code) to improve search precision.
  • Inverted Multi-Index Structure

    • Implements an inverted multi-index for organizing PQ codes.
    • Designed to improve efficiency and scalability of ANN search over large datasets.
  • Scalable Vector Search

    • Architecture suitable for building scalable vector search engines.
    • Approach validated in experiments on very large datasets (e.g., billions of vectors, as referenced in included documentation PDFs).
  • Reference Materials & Examples

    • In_Multi-Index.pdf: documentation/reference on the inverted multi-index structure.
    • PQ NN.pdf: documentation/reference on product quantization for nearest neighbor search.
    • demo.py: example script showing how to run the PQ-based ANN search.
    • toy_example/: small-scale example setup for experimentation.
    • Test/, test.py: testing-related code for validating behavior.
    • submission.py: likely a task/competition-oriented wrapper (e.g., for evaluation pipelines).
    • requirements.txt: lists Python dependencies needed to run the project.

Technology

  • Language: Python (inferred from .py scripts).
  • Distance metric: L1 (Manhattan) distance in PQ space.
  • Use cases: High-dimensional ANN search (e.g., image descriptors like SIFT and GIST), components for custom vector databases or search engines.

Pricing

  • Not applicable. This is an open-source GitHub repository; no pricing information is provided.
Surveys

Loading more......

Information

Websitegithub.com
PublishedDec 25, 2025

Categories

1 Item
Sdks & Libraries

Tags

3 Items
#product quantization
#ANN
#vector indexing

Similar Products

6 result(s)
EFANNA

EFANNA is an extremely fast approximate nearest neighbor search algorithm based on kNN graphs and randomized KD-trees. The provided implementation offers a high-performance ANN index suitable as a building block in custom vector search and retrieval infrastructure.

Reconfigurable Inverted Index

Reconfigurable Inverted Index (Rii) is a research project and open-source library for approximate nearest neighbor and similarity search over high-dimensional vectors. It focuses on flexible, reconfigurable inverted index structures that support efficient vector search, making it directly relevant as a vector-search engine component for AI and multimedia retrieval applications.

AiSAQ

AiSAQ is an all-in-storage approximate nearest neighbor search system that uses product quantization to enable DRAM-free vector similarity search, serving as a specialized vector search/indexing approach for large-scale information retrieval.

faiss-quickeradc

faiss-quickeradc is an extension of FAISS that implements the Quicker ADC approach to accelerate product-quantization-based approximate nearest neighbor search using SIMD, improving performance in vector database retrieval.

Neighbor

Ruby gem for approximate nearest neighbor search that can integrate with pgvector and other backends to power vector similarity search in Ruby applications.

AHPQ.jl

AHPQ.jl is a Julia library providing training and inference for anisotropic hierarchical product quantization, compatible with ScaNN-style vector quantization and useful for building high-performance vector search pipelines.

Built with
Ever Works
Ever Works

Connect with us

Stay Updated

Get the latest updates and exclusive content delivered to your inbox.

Product

  • Categories
  • Tags
  • Pricing
  • Help

Clients

  • Sign In
  • Register
  • Forgot password?

Company

  • About Us
  • Admin
  • Sitemap

Resources

  • Blog
  • Submit
  • API Documentation
All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
Copyright © 2025 Acme. All rights reserved.·Terms of Service·Privacy Policy·Cookies