Does anyone have advice on how I can implement data extraction from PDF? Not necessarily querying the PDF's text, but grabbing particular fields in the PDF. The PDF will have tables and fields and such, and we want to automate the extraction piece.
If you'v ever used ChatGPT on mobile, it'd be similar to how you can take a photo of something, annotate (draw a circle around it) then explain/grab that part of the image (which in our case would be some text).
I'm wondering if there's an out of the box API I can use, or if I need to go from pdf -> image -> text -> open ai api
