TanGentleman / Augmenta

Automate RAG-powered workflows
MIT License
1 stars 0 forks source link

Create demos for gpt-4o multimodality #36

Open TanGentleman opened 1 month ago

TanGentleman commented 1 month ago

I have a few test files I've been playing around with! Seems like they've really baked vision and audio into gpt-4o as a single model which is absolutely fascinating. I'll work on this alongside tool calling.