Data and AI Implementations

Everyone right now is trying to implement some kinda use case around AI. And when that happens, the focus is generally on the sexy stuff - which application functionality to implement, how to prompt engineer, etc.

However, turns out when companies are trying to implement RAG with Large Language Models, this requires tons of data migrations, preparation, and engineering.

There is no magic under which all of your corporate data just ends up in some Vector database, ready for retrieval.

So with another colleague, we decided to record an episode walking you through what exactly is involved. Check out the full version on Substack.