The Evolution of RAG Context

Retrieval Augmented Generation (RAG) systems have emerged to provide guardrails to spirited non-determinism of unfettered Large Language Models. While useful, they are clearly not enough even in the more advanced configurations of query rewriting, domain/chunk-size alignment, and re-ranking activities.

At the edge of energetic AI wave is a new form of token generation involving concepts and actions that will take things even further.