Thank you!
I have narrowed down the dataset and this helped a lot.
Furthermore, I would also suggest to carefully choose the embedding model for the FAISS index as I was using a 768 dimensional one, but switching to 368 greatly reduced computation time and gave even better results.
I have narrowed down the dataset and this helped a lot.
Furthermore, I would also suggest to carefully choose the embedding model for the FAISS index as I was using a 768 dimensional one, but switching to 368 greatly reduced computation time and gave even better results.