What you'll learn
What is RAG? And why you should still care
How RAG fits into the retrieval landscape. What problem does RAG solve?
RAG's building blocks
How chunking helps LLMs and retrieval manage context. How embedding retrieval and BM25 work.
Why RAG isn't dead
In a world of agentic search, classic RAG hasn't actually gone anywhere.
Why this topic matters
If you follow online AI chatter, you've heard that "RAG is dead". We're all just giving our agents grep now. Mature retrieval doesn't move the dial. In this talk, we'll walkthrough the building blocks and contextualize where RAG sits in a suite of solutions ranging from classic question answering to agentic search. When it's a better choice for managing context.
