Support multimodality (Image, PDF) input

Open RWL-Dittrich opened this issue 2 months ago • 6 comments

My usecase for EXO involves reading and parsing PDF's to extract data from it.

One of the requirements for this is multimodality with vision support. It would be great to have this supported in EXO through file upload.

Dec 24 '25 11:12 RWL-Dittrich

Would you like support for any specific vision model? Would this be something you want control over to choose which vision model is used to parse the PDF?

Dec 24 '25 15:12 AlexCheema

Would be great to have!

Dec 24 '25 19:12 Evanev7

Is anyone assigned/working on it?, if not I can give it a try. Sounds interesting to me.

Dec 30 '25 08:12 rafipatel

Is anyone assigned/working on it?, if not I can give it a try. Sounds interesting to me.

Assigned. Best of luck.

Dec 30 '25 13:12 AlexCheema

Hello all, let me know further steps! @Evanev7 @AlexCheema

Jan 01 '26 19:01 rafipatel