[[Neural nets|Modern technology]] has allowed converting many [[things]] to [[vectors]], allowing things related to other things to be found through finding records with the highest/highest/lowest dot product/cosine similarity/L2 distance with/to/from queries. This can be done exactly through brute force, but this is obviously not particularly efficient. [[Algorithms]] allow sublinear runtime scaling wrt. record count, with some possibility of missing the best (as determined by brute-force) match. The main techniques are:
IVF-DAC (for some reason), which is just inverted lists combined with product quantization, was historically the most common way to search large vector datasets. However, recall is very bad in some circumstances (most notably when query/dataset vectors are drawn from significantly different distributions: see [[https://arxiv.org/abs/2305.04359]] and [[https://kay21s.github.io/RoarGraph-VLDB2024.pdf]]. The latter explains this phenomenon as resulting from the nearest neighbours being split across many more (and more widely distributed) clusters (cells) than with in-distribution queries.
