harsha-simhadri/big-ann-benchmarks

Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest neighbor search methods, or vector indexes, using modern embedding datasets.

Benchmarks of approximate nearest neighbor libraries in Python

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

[NeurIPS'24] Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

Framework for benchmarking vector search engines

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

A low-latency, billion-scale, and updatable graph-based vector store on SSD.

Lightweight Nearest Neighbors with Flexible Backends