pgvector-optimization

pgvector performance optimization: HNSW vs IVFFlat index selection and tuning, ef_search / m / ef_construction parameters, iterative scanning for filtered queries, scalar and binary quantization for memory reduction, and dimensionality compression. Embedding-model-agnostic — applies to any float32 vector workload. Use when vector search queries are slow, re…

Independent GitHub snapshot · Automated classification · Original documentation governs