All, With the explosion of vision models and methods for creating embeddings from images (and PDFs!), I thought it might be useful to start a wiki page that captures some of the techniques currently in use.
There is such dynamism in the document intelligence/document engineering space that whatever we write is already out-of-date, but nevertheless, I started this: https://cwiki.apache.org/confluence/display/TIKA/Resources+for+Advanced+Document+Processing Please edit as you see fit. Best, Tim
