> "As each vector takes 2 KB space, the minimum storage space for 100 million vectors is about 200 GB"
Why are you not quantizing the vectors when you insert them? Bolt [1] and Quicker-ADC [2] make 10-100x compression basically free for approximate search (and also get you ~100x compression roughly 10x faster querying within a partition....)
Why are you not quantizing the vectors when you insert them? Bolt [1] and Quicker-ADC [2] make 10-100x compression basically free for approximate search (and also get you ~100x compression roughly 10x faster querying within a partition....)
[1] https://github.com/dblalock/bolt
[2] https://github.com/technicolor-research/faiss-quickeradc