AI engineering glossary · RAG vector search
What is binary quantisation?
Binary quantisation: Reducing every dimension of an embedding to a single bit, usually its sign, so vectors can be compared with very fast Hamming distance. It gives roughly 32-fold memory savings, and is often followed by rescoring with full vectors.
Binary quantisation: an example
A 1,024-dimension float vector becomes 128 bytes, and 10 million vectors fit in about 1.3 GB.
Related terms
More RAG vector search terms
Where you learn it
Binary quantisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.