ann-benchmarks
ann-benchmarks copied to clipboard
Add Granne
https://github.com/granne/granne
Saw this from https://0x65.dev/blog/2019-12-07/indexing-billions-of-text-vectors.html
It optimizes for storage space: Even though there are ANN libraries producing reasonable recall in less than 1 ms, for our use case we can accept sacrificing some of that speed for reduced server costs.
It seems that it only fits in their own business scenario, not in a general approximate nearest neighbor search.
@chasingegg curious if you can elaborate. what's different with the scenario they are trying to optimize for?