Approximate Nearest Neighbor Search (ANN)
Approximate nearest neighbor (ANN) search finds vectors that are very likely, but not mathematically guaranteed, to be the closest matches to a query embedding — trading a small amount of accuracy for a large gain in speed.
Part of Search Infrastructure
An exact nearest-neighbor search would compare a query against every vector in the catalog, which doesn't scale to large product counts. ANN algorithms build an index structure that narrows the search space first, which is what makes vector search practical at ecommerce scale.