Looks quite clean, congrats.
Two questions: 1. Starting from this, what would be the proper way to create embeddings for a complete document (i.e. a long paragraph)? My goal is to directly compare two PDFs according to their contents. It seems that `compute_similarity_between_strings` could be used, but then why is `get_all_embedding_vectors_for_document` useful for? 2. Using your API, does the inference run directly on the VPS? Does it need special kind of hardware (GPU, TPU or whatever)?
Sorry if my questions are dumb, but I really appreciate your project simplicity, and I want to know if it could suit my needs.
Thanks for sharing this piece of work.
;-)