I had a table in a PDF of registers and associated information, and I copied and pasted the text directly into ChatGPT as a big block, and asked it to structure the data as a table again based on its best understanding of the data, knowing it came from a table. To my surprise, it did a really good job. A couple small edits here and there were needed to change some formatting and it missed a couple values, but overall it took me a couple minutes to edit and I was on my way.
> with the only tedious aspect being the cut-and-paste between the raw data, GPT4, and the spreadsheet
My current solution is pdfplumber → GPT-3 API. I played around with a few different options, and this is personally what’s worked best for my use cases.
[1] Well . . kinda. The model has some weird ideas about what an edge table is.