Re: Increasing precision for sparse vector search

2025-05-27 Thread Michael Froh
Forgot to close the loop on this one and was traveling last week. I've gone back to the science folks with the suggestion that we experiment with 16 bits. I suspect that you're right and 16 bits will be good enough. It is good to know that we can play with it a bit, provided that we keep under th

Re: Increasing precision for sparse vector search

2025-05-16 Thread Adrien Grand
Your understanding is correct. For reference, using only 16 bits was convenient to avoid overflowing the field length, but storage efficiency was a motivation as well. Using 32 bits per frequency instead of 16 would significantly increase the size of the inverted index. We could look into what it