Free Lesson
Embeddings don't solve RAG
Part of RAG: Retrieval Augmented Gathering
60 min
Sep 28, 2026 1:00 PM
By continuing, you agree to Maven's Terms and Privacy Policy.
What you'll learn
The partial promise of embeddings in RAG
Where do embeddings sit in the family of search solutions? When does the promise fall apart
What they're not teaching you about search
From BM25, to pagerank, to late interaction, to query understanding. The pieces of search.
How to actually build RAG in 2026
It's easy to fix one problem and then inadvertantly break the rest of the product. Learn how search evals prevent that.
Why this topic matters
You've been fed a false narrative. That RAG means embeddings. Ask a retrieval engineer they'll only be one small piece of a good RAG solution. By questioning embeddings as a search solution, we'll take a chance to talk about other ways of thinking of search and retrieval. Come hang out and learn about the many ways to think about search in 2026.
