I'm running a new instance of doc intel. I have PDFs that I want to ingest and label. These are functional design specs. I saved as pdf from word. The first two pages have the yellowish background highlight to the words, and I'm able to select text. The 2nd page has a table that is automatically identified.
None of my subsequent tables get selected, so I have to manually select cell data, using the manual select tool. The same as true for 5 documents. The tables and auto labeling look like this:
I don't know what those mean, or why it doesn't recognize tables after the 2nd page. I read where a free doc intel resource limits to two pages, but I am not on a free resource. I also read about trying not to load pdfs that are saved as a single image. I'm not sure how to control that, but that might be the case from word? Other fields that it does not recognize, I've had to select manually, and I get the same symbol:
vs something in the first 2 pages, when I label it, it picks up the value right away
