Efficient KeyLLM + KeyBERT - Torch not compiled with CUDA enabled

[sam-frampton]

Testing out Efficient KeyLLM + KeyBERT in a pipeline, when the code hits the refinement stage using LLM I get error

"Error while extracting keywords from text: Torch not compiled with CUDA enabled"

This line that breaks the code inside extract keywords class - doc_embeddings = torch.from_numpy(doc_embeddings).float().to("cpu")

[MaartenGr]

Thanks for sharing this. Could you share your full code including the full error message?