Interactive Learning Lab

RAG Fundamentals

Two classes, seven labs. First the engine — how text becomes numbers, how numbers carry meaning, how a vector database searches them. Then the pipeline built on top of it.

text-embedding-3-small GPT-4o-mini Real API calls Nothing hidden
Class 5 — Semantic Search: The Engine
Why search by meaning is needed, how text becomes numbers, how the numbers carry meaning, and how a vector database scales it.
Class 6 — The RAG Pipeline
Load → Chunk → Embed → Index → Retrieve → Augment → Generate, on a real document.
The Story Arc
🤥
Lab 1
The requirement: match what the person meant, not what they typed
→
🔢
Labs 2–4
The engine: text → numbers → meaning → retrieval → the vector store
→
🚀
Labs 5–7
The pipeline: PDF → text → chunks → index → retrieve → augment → generate