ModelRefs / Learn RAG — AI Learning Pathway

Learn RAG — AI Learning Pathway

Master Retrieval-Augmented Generation from indexing to evaluation. Design, build, and evaluate production-grade RAG systems. A 28-hour intermediate path.

Overview

Master Retrieval-Augmented Generation from indexing to evaluation.

What you will be able to do

  • Architect a production RAG pipeline
  • Choose embedding + vector store correctly
  • Implement chunking, reranking, and evaluation
  • Ship a RAG service with observability

Pathway phases

  • Foundations — Embeddings, chunking, vector stores.
  • Retrieval — Hybrid search and reranking.
  • Production — Eval, observability, cost control.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Learn RAG — AI Learning Pathway.

Frequently asked questions

What will I learn in Learn RAG?

Architect a production RAG pipeline Choose embedding + vector store correctly Implement chunking, reranking, and evaluation

How long does Learn RAG take?

Approximately 28 hours across 3 phases.

What projects are included?

Internal Helpdesk RAG • RAG Evaluation Harness • Cited Answers Service • Cost-Aware Retrieval Router