Open alexyalunin opened 1 month ago
Hi @alexyalunin! Did you only change the dtype in the constructor or somewhere else?
Can you please log the type of the input matrix and the hardware_capabilities
of the index?
train_matrix.dtype dtype('float32')
Idk how to log hardware_capabilities, here is index
usearch.Index
I didn't change dtype of index by myself. In the example I changed dtype to bf16 to reproduce the problem
I have just rebuilt the index 5 times in a loop and look at 5 anchor items (i.e. 25 examples).
It seems like even with f16 the problem still exists, it is just less often than with bf16. It also seems like with the old version (2.12.0) the problem doesn't exist, so I guess I will just stay with an old version.
Interesting 🤔 Thank you, @alexyalunin! I will look into it!
Found the issue in the underlying SimSIMD library. Investigating. Hope to merge within 24h.
Describe the bug
Just updated library from 2.12.0 to 2.15.3 Now I'm getting irrelevant closest items.
I expect for an anchor item to be closest to it by any metric (I use cos), you can see in Expected behavior screenshot. Now after update anchor item is not closest + I get a lot of irrelevant items for it (see the screenshot).
It turns out the difference is in dtype='bf16' which is default in new version. After reverting it back to dtype='f16' I get an expected behabior.
Steps to reproduce
Here is the code I use
Expected behavior
using dtype='f16'
USearch version
2.15.3
Operating System
Ubuntu 20.04.6 LTS
Hardware architecture
x86
Which interface are you using?
Python bindings
Contact Details
ale.yalunin@gmail.com
Are you open to being tagged as a contributor?
.git
history as a contributorIs there an existing issue for this?
Code of Conduct