# Revision: Cheat Sheet and Self-Check — Retrieval-Augmented Generation (RAG)

Source: https://www.geekswithgeeks.com/en/rag/z-revision

> Review the key ideas of the whole course.

## Cheat sheet

**Idea**: retrieve relevant chunks, augment the prompt, generate a grounded, cited answer. **Ingest**: clean extraction, structure-aware chunks (200 to 500 tokens, small overlap), metadata for filters, permissions and citations. **Retrieve**: BM25 for exact terms, embeddings for meaning, hybrid with RRF, ANN indexes at scale. **Improve**: query rewriting, cross-encoder reranking, MMR for diversity, tuned k with a relevance threshold. **Generate**: numbered context, "answer only from context", verify citations in code, groundedness check, graceful refusal. **Evaluate**: golden set, recall@k and MRR, faithfulness, unanswerable questions, failure tally by stage. **Production**: incremental updates, access control, injection defence, latency and cost controls; add agentic or graph RAG only when measured need appears.

**Quiz:** Users search with "work from home" but the policy says "remote work". Which retrieval method helps most?

- [ ] Lowering the temperature
- [ ] Exact keyword match only
- [ ] Increasing chunk overlap
- [x] Embedding (semantic) search, ideally combined with BM25

*Answer:* Embedding (semantic) search, ideally combined with BM25. Embeddings bridge different wording; BM25 still covers exact terms.

**Quiz:** Which number best tells you whether retrieval is finding the evidence?

- [ ] Average word length
- [x] Recall@k on a golden set
- [ ] GPU temperature
- [ ] Number of files

*Answer:* Recall@k on a golden set. Recall@k measures how often relevant chunks appear in the retrieved set.

**Quiz:** What is the safest way to enforce per-user document access?

- [ ] Ask the model not to reveal secrets
- [x] Filter in the retrieval query so forbidden text is never fetched
- [ ] Hide it in the UI
- [ ] Rely on chunk size

*Answer:* Filter in the retrieval query so forbidden text is never fetched. If forbidden text reaches the prompt, it can leak.