Luis Roque

The process should at least give a better trace of the error since it is hard to understand what is happening at first sight. It could be a bit dangerous...

I think the use case here is not to process very large documents (for that, you have to consider other approaches such as using a vectorDB and semantic search) but...

Simply using CUDA and CUDNN installed from pip wheels worked for me (NVIDIA GPU): ``` pip install --upgrade pip # CUDA 12 installation # Note: wheels only available on linux....

I am having the same issue exactly