🔍Paid course
RAG That Works: Retrieval, Not Magic
Why your document chatbot answers badly: chunking, the real limits of embeddings, hybrid search, reranking, and how to measure each step.
🔍
RAG That Works: Retrieval, Not Magic
🎓 3 levels📚 12 lessons
1. Why Retrieval Fails
- •RAG is search before it is generation
- •Chunking: the decision with the most impact and the least thought
- •Embeddings: what they capture and what they do not
- •Measuring retrieval on its own
2. Retrieving Better
- •Hybrid search: why BM25 is still alive
- •Reranking: the step almost nobody adds
- •Metadata and filtering: the cheapest improvement
- •The user's question is not the search query
3. RAG in Production
- •Lost in the middle: context order matters
- •Citing, and knowing how to say you do not know
- •The index changes: maintenance and data that expires
- •When RAG is not the answer
$10one-time payment
Interested in more courses?
Kolibrí Pro gives you the entire catalog, including new courses as they launch, from $19/mo.
See all plans →