Systém je důležitější než model
The first observation is really that language models are awesome, but often they're only 20% of a much bigger system. If you have an Enterprise AI deployment, usually that means it's a RAG system. [...] RAG is really kind of the standard way that you get generative AI to work on your data.
What happens very often these days is a new language model comes out, and everybody goes, "Whoa, new language model, it's great!" Everybody starts to think just about the language model, but very few people actually think about the system around the language model. That system needs to solve the problem. You can have a relatively mediocre language model but an amazing RAG pipeline around it, and that's going to be much better than an amazing language model with a terrible RAG pipeline around it.
The basic observation here or the lesson is that you should be thinking about systems, not about models. The model is only a small part of the system, and the system is the thing that solves the problem.
-- Douwe Kiela: "RAG Agents in Prod: 10 Lessons We Learned"