This looks solid, being able to search across diagrams and videos is a big win. Curious how well it performs with noisy scanned PDFs or annotated images.
Thank you!! It works particularly well with those. We use ColPali-style embeddings for our visual doc search. As a result, we're not limited by parsing quality the same way typical RAG systems are. Here's a link to a blog I wrote on ColPali, for reference: https://docs.morphik.ai/concepts/colpali