News for hackers. Stuff that matters.
Re:Haystack DB – 10x faster than FAISS with binary embedding... by matharmin on Monday April 29, 2024 @08:12AM (#40197293)
This sounds like the "Closest pair of points problem", which should have fast solutions - O(n log(n)) comparisons instead of O(n^2), which makes a huge difference when you have 10 million vectors. You might not find an off-the-shelf solution, but there are some good explanations of the approach at least.

There are no comments on this comment yet.