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.

We will cover:

• A brief overview of RAG systems and the issues that remain
• The Sonar Embedding model and how it forms the basis of Large Concept Models (LCMs)
• The various Action-based embedding models for physically and digitally-embodied agentic systems
• Use cases that emerge from these advanced, multi-lingual, multi-modal developments in the ever-changing world of generative AI

About Brian Sletten

Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, AI/ML, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.

More About Brian »