06. Module 07 Review — RAG Fundamentals¶
Focus: chunking, embeddings, vector search, pipeline failure modes, and retrieval evaluation.
Review loop¶
- Skim the TOC in
02_explainer.md. Mark any chapter you cannot explain cleanly. - Re-answer the self-check questions in
01_weekly_plan.mdwithout looking. - Re-do the hardest prompts in
04_daily_recall.mdfrom memory. - Sketch the failure-fix table from explainer §6.1 — at least 8 rows — without looking.
- Review
05_hands_on_lab.mdand write one thing you would keep, one thing you would change, and one failure you still do not fully understand. - Re-read the production notes in explainer §6.4 and say the latency budget out loud from memory.
- Re-read the foundation-gap audit in explainer §6.6 before starting Module 08.
Reflection¶
- Which concept now feels automatic: chunking, embeddings, vector search, or evals?
- Which one still feels slippery under interview pressure?
- What failure mode would you test first if this system shipped tomorrow?
- What should feel automatic before starting
09_advanced_rag_patterns?
Embedded checkpoint¶
Conceptual¶
- Why is hallucination especially dangerous for private-company facts? (§1.1-§1.4)
- Chunk size trade-off — too small vs too large? (§2.2)
- Why use overlap? When does overlap become wasteful? (§2.3)
- Recursive splitting vs semantic splitting — when each? (§2.4)
- What do embeddings capture, and what do they miss? (§3.1)
- Cosine vs dot product — when same ranking? (§3.3)
- HNSW vs IVF — what idea makes each fast? (§3.5)
- Why does reranking help? (§4.5)
- Recall@k vs MRR vs NDCG — what is each measuring? (§5.2-§5.4)
- Faithfulness vs answer relevance — what is the difference? (§5.5)
- Why does RAG not automatically solve multi-hop reasoning? (§4.9)
Applied¶
- Pick one corpus you know well. What chunking strategy would you start with, and why? (§2.4-§2.6)
- Design a sub-1 second RAG response budget. How much time goes to embed, retrieve, rerank, and generate? (§6.4)
- If recall@10 is low, what three things would you inspect first? (§2.2, §3.4, §4.4)
- If the answer is fluent but unsupported, where can the bug live? (§4.6, §5.5)
- How would you explain the difference between Week 7 and Week 8 in one sentence? (§6.7)
Foundation-gap audit¶
Before you move to 09_advanced_rag_patterns, these basics must be automatic:
- [ ] Basic RAG pipeline
- [ ] Embedding similarity concept
- [ ] Chunk size reasoning
- [ ] Vector search mechanics
- [ ] Retrieval metrics
Bridge¶
Next module — 09_advanced_rag_patterns — tackles the hard cases: multi-hop questions, query rewriting, HyDE, agentic RAG, and production hardening.
Completion gate¶
- [ ] All 6 explainer sections read at least once
- [ ] Weekly plan completed
- [ ] Assignment shipped with retrieval metrics
- [ ] Failure-fix table from §6.1 reconstructed from memory
- [ ] Foundation-gap audit checked honestly
- [ ] Ready to move to Module 08