Jonah Lynch

faster performance on older machines

15

On machines with smaller memory and slower processors, it can be useful to reduce the overall number of threads running. For instance on my MacBook Pro Intel i5 16Gb machine,...

This is working code, with modifications to put embeddings and models to the mps device if available. Centralized device definition using from vec2text.models.model_utils import device HOWEVER it does not improve...

Apple Silicon support

3

Thanks Jack for your very interesting project. I see that MPS support is implemented in the code, but I'm not seeing it used on my machine. On my machine, torch.backends.mps.is_available()...

add delay to avoid rate limits

1

simple time.sleep() parameter to add delay ## Summary by CodeRabbit - **New Features** - Introduced a new parameter, `delay`, in the process of handling sources to manage rate limits with...