It was great fun to pick up and complete the RAG course, which gives enough high level architecture design concepts but also production related software design details.
I am hoping we could have course of similar depth and production focus for multimodal RAG. I took the Building Multimodal Search and RAG (https://www.coursera.org/projects/building-multimodal-search-and-rag), it is a good begineer intro, but only scratches the surface.
Can any deep learning.ai staff help share if there are any intiatives in multimodal in-depth courses on qwen vl, gemma, nvidia cosmos eta?