How do vector databases differ from traditional databases?

medium

Answer

$Optimized for approximate nearest neighbor (ANN) search on high-dim vectors.$
$Core index types: HNSW (graph, fast, memory-heavy), IVF (inverted-file, memory-light), IVF-PQ (product quantization), ScaNN, DiskANN.$
$Also handle metadata filtering (usually via a bitmap or pre/post-filtering pass), hybrid search (dense + BM25), and incremental updates.$
$Examples: Pinecone, Weaviate, Qdrant, Milvus, Chroma; also Postgres pgvector, Elasticsearch, MongoDB Atlas.$
$Choose by scale, filter needs, and existing stack.$

Check yourself — multiple choice

Same as SQL DB
Optimized for high-dim ANN search (HNSW, IVF-PQ) + metadata filtering + hybrid search — Pinecone, Qdrant, pgvector, Elastic
Only for embeddings training
No indexing

Vector DBs: ANN indexes (HNSW / IVF / PQ) + filters + hybrid — Pinecone, Qdrant, pgvector...

#vector-db#retrieval

214 interview questions in this topic.