pgvecto.rs

Open-source PostgreSQL extension for SQL vector similarity search with HNSW and IVFFlat indexes enabling efficient ANN on embeddings. Supports hybrid queries blending vector search with SQL filters and metadata, ideal for in-DB RAG, analytics, and similarity tasks. Cost-effective alternative to dedicated vector DBs like Weaviate, leveraging existing Postgres without data movement or extra services.

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.

Rust core for high-performance on-device HNSW vector search with SIMD and compression, achieving low-latency multi-threaded queries for edge AI RAG. Up to 3,597 QPS; optimized for real-time vs cloud alternatives.

Pure-Rust implementation of HNSW algorithm for approximate nearest neighbor search. Decouples graph from vector storage for flexible deployment. Supports dense floating point and quantized int8 vectors. This is an OSS library.

Qdrant Cloud is a serverless, cloud-hosted managed vector database with auto-sharding, scaling, pay-per-use pricing, automated backups, advanced filtering, and multi-region deployments. Tailored for enterprise RAG and high-scale production AI applications. Delivers easier operations than self-hosted Milvus or Qdrant, with superior performance vs Zilliz in complex queries.

Hybrid billion-scale vector search method combining HNSW with inverted file indexes, enabling cost-efficient search by keeping centroids in memory while storing vectors on disk.