Q: Image recognition? Charts, tables, graphs
Does paperguide have the ability to understand images such as using openAIs vision API? For example if we're uploading a PDF research paper and that PDF includes graphs and charts of data , Is it able to understand the graphs and charts by using some sort of a vision or image recognition?
Roop_Paperguide
Nov 8, 2024A: Hi, thanks for your question! We currently have both OCR and OpenAI Vision integrated. However, while OCR can handle text extraction, it doesn’t directly work for complex graphs or charts by default when you first upload. After uploading a document, though, you can use the snipping tool to select any graph or chart and ask a follow-up question.
WhatNuwithyouPLUSDoes the OCR use the credits? If I want to do computer vision? Can I also plug in Google vision?
WhatNuwithyouPLUSAka cloud vision
steven408PLUSSome of your competitors offer the ability to automatically extract graphs and images from PDFs without needing to manually snip them - is this something you're looking to add?