Learn vector search with Rust and DataFusion; the C++/BusTub track is deprecated.
VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.
Embedded retrieval library built on Parquet. Fast, efficient, and scalable.
Billion-scale embedded vector database built entirely on Parquet and Arrow.
Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement
PostgreSQL TurboQuant Index for PGVector
High-performance database management system
GenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
GenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
Locality-Sensitive Hashing (LSH) using Random Hyperplane Projections for sublinear approximate nearest neighbor search under Cosine distance.
Locality-Sensitive Hashing (LSH) using Random Hyperplane Projections for sublinear approximate nearest neighbor search under Cosine distance.
⚡ Blazing-fast GPU vector search for PostgreSQL powered by NVIDIA cuVS.
DiskANN vs HNSW: a measured vector-index benchmark at 3.38M and 10K scale (recall/QPS/memory, concurrency, reproducible harness)
Hybrid B+ Tree and HNSW index for efficient k-NN search with scalar filtering using probabilistic optimization
A library that's just an in-process indexer: A lightweight Rust engine with Python bindings for HNSW, PQ, and Flat that runs entirely on your local machine without devouring your RAM
Comparing attribute-set representations (linear/blocked bitsets, Roaring) for filtered HNSW search.
TurboQuant-style HNSW benchmark on GloVe-200: Recall@10 vs compression across 1-8 bits.
All nearest-neighbor search using neighborhood graphs
AI-powered vector database with HNSW indexing, FastAPI server, WAL persistence, distributed sharding, and RAG pipeline integration
Python library for MUVERA multi-vector retrieval via Fixed Dimensional Encodings. ColBERT / ColQwen2 / ColQwen3.5 compatible.
To associate your repository with the approximate-nearest-neighbor topic, visit your repo's landing page and select "manage topics."