Real RAG talk · AI Automation Society

Real RAG talk

I'm diving deeper into RAG right now and would love to hear what you're building with it.

Not the theory.

The projects. The fails. The learnings.

A few questions I'm curious about:

What RAG projects have you shipped so far?
Where do you see the biggest strengths of RAG?
Where do you see (current) weaknesses or even limits of this technology?
Which vector store or database do you use?
Do you choose embedding model and chunk size individually, or do you have standard sizes that have become your gold standard?
How do you implement your RAG pipelines? Low-code tools like n8n, pure code, or something else?

Super curious to hear

2 comments