Originally published at: https://developer.nvidia.com/blog/accelerated-vector-search-approximating-with-rapids-raft-ivf-flat/
Performing an exhaustive exact k-nearest neighbor (kNN) search, also known as brute-force search, is expensive, and it doesn’t scale particularly well to larger datasets. During vector search, brute-force search requires the distance to be calculated between every query vector and database vector. For the frequently used Euclidean and cosine distances, the computation task becomes equivalent…