>>106011033>I said and save hours of work.you have 0 idea what you are talking about, the kind of models I am telling you works on CPU and will take you ms to classify your images or you can even use CLIP
there are hundreds of examples of how to do this https://docs.llamaindex.ai/en/stable/examples/multi_modal/image_to_image_retrieval/
I literally can implement this solution in 30 minutes (I had build many semantic systems)
what you are suggesting is slow af