Your data preparation matters more than your tech stack

It's not great to just give it access to your drive and say, 'Reason all over this knowledge base.' It actually does a very poor job understanding importance of the past and putting weights on stuff. You actually want to think about specifically what the context when do you want to give it to and what's the knowledge base that you want to have it focused on.

In a lot of the companies that I have seen, that's the biggest performance, in their RAG solutions coming from better data preparations, not agonizing over what vector databases to use.

LLMs can only be as good as the data they are given and how recent that data is. They're ultimately like information shredders. They are limitless information eaters. You can never have enough information to give to an LLM to truly gain its value.

The difference between the right context and not, it's entirely the difference between a good answer and a bad answer.