• Home
  • Categories
  • Tags
  • Pricing
  • Submit
  1. Home
  2. Sdks & Libraries
  3. AHPQ.jl

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.

🌐Visit Website

About this tool

AHPQ.jl

Description

AHPQ.jl is a Julia library implementing the Anisotropic Hierarchical Vector Quantizer based on the Scalable Nearest Neighbours Algorithm (ScaNN). It follows the Google Research implementation (per the referenced paper and talk) and provides a configurable Max Inner Product Search (MIPS) system, written entirely in Julia with no non-Julia dependencies.

  • Category: SDKs & Libraries
  • Technology: Julia
  • Use cases: Vector search, product quantization, MIPS-oriented indexing
  • Source: https://github.com/AxelvL/AHPQ.jl

Features

  • Anisotropic Hierarchical Vector Quantizer

    • Implements anisotropic hierarchical product/vector quantization.
    • Trains a vector quantization tree (VQ-tree) with an anisotropic loss function.
    • Optimized for Max Inner Product Search (MIPS) rather than standard L2 distance.
  • ScaNN-based Algorithm

    • Based on Google Research’s Scalable Nearest Neighbours Algorithm (ScaNN).
    • Follows the approach described in the associated research paper and SlidesLive presentation.
  • IVFADC-style Architecture

    • Can be viewed as an IVFADC setup (inverted file with asymmetric distance computation).
    • Uses vector quantization for coarse partitioning and refined distance evaluation.
  • Julia-native Implementation

    • Written 100% in Julia.
    • No non-Julian dependencies, easing installation and integration into Julia projects.
  • Configurable MIPS System

    • Provides a highly configurable Max Inner Product Search pipeline.
    • Designed for building high-performance vector search systems using product quantization.

(The repository content snippet does not expose further API-level or configuration details.)


Pricing

  • Not applicable (open-source library; no pricing information provided in the available content).
Surveys

Loading more......

Information

Websitegithub.com
PublishedDec 25, 2025

Categories

1 Item
Sdks & Libraries

Tags

3 Items
#product quantization
#Julia
#vector search

Similar Products

6 result(s)
NearestNeighbors.jl

NearestNeighbors.jl is a Julia package implementing various nearest neighbor search algorithms and index structures for high-dimensional vector data.

Milvus Lite

Milvus Lite is a lightweight, pip-installable variant of the Milvus vector database that runs as a library in notebooks or laptops, ideal for learning, experimentation, and rapid prototyping of AI and vector search applications.

HNSW (Go)

A Go implementation of the HNSW approximate nearest neighbor search algorithm, enabling developers to embed efficient vector similarity search directly into Go services and custom vector database solutions.

HNSW (Rust)

A Rust implementation of the HNSW (Hierarchical Navigable Small World) approximate nearest neighbor search algorithm, useful for building high-performance, memory-safe vector search components in Rust-based AI and retrieval systems.

jvector

jvector is a high-performance Java-based library and engine for vector search and approximate nearest neighbor indexing.

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.

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