How to use text and image as openAI single prompt

Hello Folks, I was trying to develop an AI-powered Glide app designed to generate scientific content. I am struggling to use ‘text’ and ‘images’ together as prompts to generate content since they are located in different columns. Appreciate any help .

So you want to use image in the prompt as well? That’s not supported yet inside Glide. You would have to do an external API call to use GPT-4 Vision.

Are you using this? The Image field use’s a file url


Wow is this new? Thanks for this!

Thanks for reply. is this new? How to do that? I was doing following ,See Pic arrow


Seeing as you have multiple images in “Figure” columns, I would suggest using a make array column to combine them, then use that array in the Images field.