Learning Materials

RAG, AI, and LLM concepts — taught as a senior engineer with no ML background. 4 lessons · 4 reference cheat sheets.

Lessons

• Lesson 0001 — Embeddings: A Vector of Meaning
  Anchored in rag_pipeline.py → class Embedder · config.py → MODEL_NAME = "all-MiniLM-L6-v2"
• Lesson 0002 — Vector Search at Scale
  Anchored in rag_pipeline.py → class VectorStore · vector_search
• Lesson 0003 — BM25: Why Keyword Search Still Matters
  Anchored in rag_pipeline.py → class BM25Index · config.py · BM25Index.search
• Lesson 0004 — RRF: the tiebreaker that fuses two rank lists
  You have a vector search that scores 0–1 and a BM25 search that scores 0–30. Adding them is meaningless. Reciprocal Rank Fusion sidesteps the whole scale problem by using ranks, not scores. This lesson walks through the

Reference cheat sheets

• BM25 Cheat Sheet
  Quick reference. Pair with lessons/0003-bm25-keyword-search-still-matters.html.
• Embeddings Cheat Sheet
  Quick reference for the rag-blog stack. Pair with lessons/0001-embeddings-vector-of-meaning.html.
• RRF Cheat Sheet — Reciprocal Rank Fusion reference
  Printable. Designed to live next to your editor.
• Vector Index Cheat Sheet
  Quick reference. Pair with lessons/0002-vector-search-at-scale.html.