Hello, I am working on an agent in GPT Enterprise for a company. The goal is document identification. In the tests conducted, it is only allowed to upload documents in image formats, such as JPEG and PNG. I was asked about the possibility of using files in PDF format. Is this possible? If not, is there a plan to make this available in the Enterprise version?
Yes, plus more
We currently support PNG (.png), JPEG (.jpeg and .jpg), WEBP (.webp), and non-animated GIF (.gif).
https://platform.openai.com/docs/guides/vision/what-type-of-files-can-i-upload
No, you need to convert them into an image. You lose any inline data as a result. You can extract it first, try to understand it, and send it alongside the image if you’d like
Is there a possibility to accept PDFs in the future, or is this something that OpenAI is not currently focused on?