I have a PDF document with multiple pages, where each page corresponds to a different type of form or model. I need to classify each page first and then apply data extraction accordingly.
I’ve already trained two custom models using a Document Understanding (DU) modern project, but I’m not sure how to perform page-level classification in Studio Web and then extract the required information from each page.
Since my PDF contains multiple page types, and some page types repeat across several pages, I need a way to handle this effectively.