Ivfflat Inverted File Approximate Indexing With Clustering Based Partitioning

via “ivfflat inverted-file approximate indexing with clustering-based partitioning”

Vector search for PostgreSQL — HNSW indexes, similarity queries in SQL, use existing Postgres.

Unique: Uses k-means clustering to partition vectors into inverted lists, then performs exact distance calculation only within top-k nearest clusters. This approach trades recall for memory efficiency and index build speed, making it suitable for billion-scale deployments where HNSW memory overhead is prohibitive.

vs others: More memory-efficient than HNSW for 10M+ vectors (1-2x vs 8-12x overhead), and faster to build (O(n) vs O(n log n)), making it better for cost-sensitive cloud deployments where storage is the primary constraint.

via “inverted-file index construction with clustering”

A library for efficient similarity search and clustering of dense vectors.

Unique: Implements k-means clustering with Faiss-specific optimizations like batch k-means and GPU-accelerated centroid updates (in GPU version), plus automatic handling of empty clusters and centroid reassignment. Integrates clustering directly into the search index rather than as a separate preprocessing step, enabling joint optimization of cluster quality and search performance.

vs others: More efficient than scikit-learn's k-means for large-scale vector clustering because it uses batch updates and avoids dense distance matrix computation; tighter integration with search than standalone clustering libraries, enabling co-optimization of index structure.