Micro Free Course — 100% Free Learning
All lessons in this module are free to learn. Sign in with Google to save your progress.
2
M2 — RAG Architecture + Evals
RAG vs fine-tune trade-offs, citation/faithfulness evals with judge-bias guards, eval-set authoring.
Module Progress0% Complete
59 min total
4 Lessons
0 Completed
Module Content
RAG Architecture + Trade-offs
Outcome: Choose RAG vs fine-tune for 3 cases Curated video (IBM Technology): What is Retrieval-Augmented Generation (RAG)? — https://www.youtube.com/watch?v=T-D1OfcDW1M (verified live via yt-dlp 2026-09-24). Pointer: llms-genai-for-practitioners/12 (hybrid legal-AI pattern); shell: courses/video-scripts/genai-rag-agents/03.md.
7 minVideo
Start
RAG Evals: Citations / Faithfulness / Cost-Latency
Score with binary gates + 1-5 scales; guard judge bias.
30 minArticle
Start
Quiz: RAG + Evals
10 scenario MCQs, Bloom 3-4, gate >= 80.
20 minAssignment
Start
Citation-Required Eval Set + Report
Submit eval set + groundedness/refusal/cost-latency report.
minSubmission
Start