A 128-dimensional float32 vector takes 512 bytes. Product quantisation (PQ) compresses it to a handful of bytes: split each vector into m sub-vectors, learn a small codebook of k centroids per sub-space, and store just the centroid ids.
Unlock this and every premium problem across all tracks — plus hidden-test grading, advanced AI engineering modules and new content every week.
Start 7-day free trial