Can Coda AI do this? (Images, PDFs, files...)

1

I have two scenarios for Coda AI:

  1. File column - upload a PDF document, in the other text column, I want Coda AI to summarize what is in the PDF file.
  2. File/image column - upload social media post design, in the other text column I want Coda AI to be able to read that design and create social media caption with hashtags and etc.

So my question is can Coda AI or Chat GPT plugin read into PDFs, images…
Maybe there is some other Vision AI plugin to make it work?

Thank you!

1 Like
2

Hey there!
I have two packs that might help you:

  • PDF Pack lets you extract pure text from a PDF
  • OCR Pack lets you extract text from PDFs, even ones that contain images, and you can also feed it images directly

Once you have the text of these media files you can feed that to Coda AI :+1:

3 Likes
3

Thanks a lot! PDF pack looks awesome :muscle: :fire:

1 Like
4

Another option is: use the Make.com w/ payload pack, send it to Make, and there you can insert steps to use even chatGPT vision to extract information, and send it back to the row.

1 Like
5

thanks, will test this options as well.