I enjoyed this video from Kristian Freeman from Cloudflare on building something quickly with their AutoRAG feature. RAG (Retrieval-Augmented Generation), as I understand it, means that you’re going to ask an AI model a question, but you want that answer informed by a whole corpus of documents. As in, ask the question “how do I animate a line like it’s being drawn?” and have it be informed by every single blog post I’ve ever written. This feature means you can chuck those blog posts in an R2 bucket and with a bit of setup it does the rest. Feels like how this stuff ought to work.
Cloudflare AutoRAG
Chris Coyier
on
