Applied AI·Embeddings and retrieval
you pick the cheaper, smaller index because the machine is memory-bound, and accept lower recall at the same speed.
IVFFlat
Draft summary, pending review
An older ANN approach: cluster vectors into lists, search only the closest lists. Cheaper to build and smaller than HNSW, usually lower recall at the same speed. pgvector offers both; start with HNSW unless memory forces otherwise.