Filtered-DiskANN

NeurIPS 2023 paper presenting NHQ, an efficient and robust framework for approximate nearest neighbor search with attribute constraints, enabling hybrid queries combining vector similarity with structured filtering.

An efficient indexing approach for multi-tenant vector databases that handles low-selectivity filters effectively. Curator addresses the challenge of maintaining high performance when serving multiple tenants with filtered vector search queries.

Joint Attribute Graphs for Filtered Nearest Neighbor Search, a research paper that addresses the challenge of combining vector similarity search with attribute filtering. JAG presents a novel index structure that efficiently handles filtered ANN queries common in real-world applications.

Timescale extension for pgvector introducing StreamingDiskANN for disk-optimized, high-recall ANN search (28x lower p95 latency vs Pinecone), with hybrid SQL+vector capabilities. Supports binary quantization, filtered queries; scales RAG/analytics to billions on existing Postgres without sharding.

SQLite fork with native DiskANN vector search, enabling hybrid SQL+vector on production-ready embedded relational infra with ACID. Leverages existing SQLite apps vs dedicated VDBs.

PostgreSQL extension stack (pgvector + pgvectorscale + pgai) adding StreamingDiskANN for hybrid SQL+vector search with ACID transactions on existing Postgres infra. 11x QPS advantage over Qdrant at scale; cost-effective vs dedicated VDBs.