AI Engineering · 200-level

RAG Foundations

AIE-2023 creditscorebadge: rag-iprereqs: AIE-103
Start this course — free

Earn the rag-i credential

What's inside

Sections & lessons

01

Why retrieval

  • Grounding, and when RAG beats fine-tuningconcept45 min
02

Chunking strategies

  • Size/overlap tradeoffs and the cost consequenceconcept45 min
03

Chunk Slicer lab

  • Watching search quality rise then crash as one slider movesconcept90 min
04

Embeddings & vector similarity

  • How similarity search works, made literally draggableconcept45 min
05

Vector stores in practice

  • pgvector in practice: indexing and nearest-neighbor lookupconcept60 min
06

Retrieval: top-k & filters

  • Ranking chunks and filtering the candidate poolconcept45 min
07

The lost-answer failure mode

  • Watching a correct chunk never make the visible top-kconcept60 min
08

Grounded generation

  • Citations and refusal on low confidenceconcept60 min
09

Lab + eval-gate: build a RAG bot

  • RAG Sandbox graded lab — retrieval score ≥ threshold (RAG I badge)concept120 min

This module ends in a gate you can fail.

That's what makes passing it mean something. Take the DSAT, get placed, and start earning.