IVF index
An approximate vector index that clusters vectors into cells and searches only the cells whose centres are closest to the query.
In more detail
The nprobe setting chooses how many cells to search: more probes find more true neighbours at more cost. FAISS and pgvector's ivfflat use it; recall drops when the right answer sits just across a cell boundary.
Related terms
- HNSW — An approximate vector index built as a layered graph of links between nearby vectors, searched by walking from a coarse top layer down to a dense bottom one.
- approximate nearest neighbour search — Vector search that skips most comparisons using an index, trading a little recall for much faster queries.
- FAISS — Meta's open-source library for fast similarity search over dense vectors, with flat, IVF, HNSW and quantised indexes.
Taught in
- Vector Indexes And Databases — AI Engineering: LLM Apps, RAG & Agents