1 🗺️ Why vector DBs
The library sorted by MEANING — keywords match strings, not ideas.
2 🔢 Text to vectors
Giving every text a seat — our honest toy vs learned embeddings.
3 📐 Similarity
Direction beats distance — and the normalize-then-dot trick.
4 🏃 Nearest neighbors
Asking everyone vs the friendship map (HNSW) — the recall dial.
5 🔬 Build a vector DB
70 honest lines: embed, cosine, store, filter, top-k.
6 ✂️ Chunking & metadata
Cards and colored stickers — the quality lever bigger than any index.
7 📖 RAG wiring
The open-book exam, end to end — with OUR page-finder.
8 🏬 The landscape
pgvector, Pinecone, Chroma, FAISS — picking without a bake-off.