PDF Q&A App using ColPali, Modal, and FastHTML
Lately, I’ve been following FastHTML from a distance. As someone who sticks to backend Python development, frontend development has always been a bit foreign to me, but I’m interested in giving it a shot. FastHTML feels like a good way to get started with some basics by building small apps.
I’ve also noticed a lot of chatter on X about Colpali and document retrieval with vision language models, which caught my attention. I like exploring new stuff so I want to see what that is all about.
On top of that, I’m still enjoying Modal, which I’ve written about before here and here. I thought it would be fun to combine these tools into a simple app and see what I can learn from it.
There are already so many great resources out there about ColPali. Checkout the resources below for more information. I will give a quick overview.
Remember that with Modal, you only pay for compute when running requests in active containers. My deployed app can sit there idle without costing me anything!
