RAG Systems
topic on 3 shows · 3 statements across 3 episodes
No Priors 
the Official SaaStr Podcast 
the MAD Podcast
3 statements about RAG Systems, every show
Adams: AI systems are easier to build when decomposing workflows discretely
“Getting AI and getting a rag system
to accurately do these things is easier when it's discrete. You can experiment much faster. You can solve bits of the problem independently and then kind of chain them together.”
Kiela: Advanced RAG systems break down when scaling to a million PDFs
“You can build a very awesome demo on a couple of PDFs and things will probably work. But then you have to scale it up to a million PDFs, and then everything breaks down. And the reason for that is that a lot of these kind of advanced RAG systems still actually…”
Overestimating LLM Flexibility Causes Repeated Enterprise RAG Failures
“Well, I think all language models are quite sensitive to prompts, to the way that you present data. They all have their own individual quirks. The way that you talk to one might not work for the way that you talk to another. And so when you're building a syste…”