Hello everyone, I need some info from experts like you
What I need to do via API is to give it access to a folder on my google drive, inside this folder i’ve different images (or I can have pdf with multiple images inside it) and a spreadsheet. Those are invoices, payments and other kind of similar documents). What I would like to ask is to recognize simple data like invoice number, invoice data, totale invoice in € and so on. I can easily do it on chat gps (i load 3/4 images and ask to find this infos) but I need to do it via API because I need to do in thousands of files. Can someone help me out to understand what to do and if it’s possible to do it? It’s easier to do it with jpg or with pdfs? I’ve notice that doing it with OCR is worst than giving the images directly. The results are much more accurate with the images on chatgpt chat. After that i need to put this info in the spreadsheet.
I need help just for the image manage part. The rest is easy.
Thanks in advance to everyone who can helps me