pgvector-optimization

【效率与协作】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 s…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准