Hey gang -
I just released a new OpenAI Vision Pack allowing image URLs to be processed through OpenAI’s Vision.
This can be pretty amazing for creating packs that transcribe notes or journal entries; catalogue books, records, art, recipes, etc.; inventory products; and more.
This pack does require the images to either be in base64 or saved as imageURLs, so I’d suggest using it in conjunction with the imageURL pack.
Would love to hear what you think!