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
Learn it from the inside
This module's playgrounds
AI Engineering
Next in this path
Where this specialization goes from here — in (level, code) order.
Vocabulary
Key concepts in this course
Retrieval-Augmented Generation (RAG) Grounding Chunking Embedding Cosine Similarity Vector Database HNSW Index Reranking Recall@k
Compare related approaches
Optional · watch & try
Go deeper, elsewhere
Hand-picked public explainers and open tools — always optional, never required, never graded.
Introduction to Vector Embeddings and Vector SearchFoundational explanation of turning text into vectors for similarity search Embeddings & Vector Databases ExplainedConnects embeddings to how a vector database actually stores and searches them Vector Databases simply explained! (Embeddings & Indexes)Covers embedding indexes (e.g. HNSW) at a beginner level Embedding Projector (TensorBoard, Hugging Face Space)Interactive 3D projection of embedding vectors to see semantic clusters and analogies Retrieval Augmented Generation (RAG) Explained in 8 Minutes!Fast end-to-end mental model of the RAG pipeline · ~8 minRAG Explained in 12 MinutesSecond angle on the same pipeline with a different worked example · ~12 min
This module ends in a gate you can fail.
That's what makes passing it mean something. Sit Chuun, get placed, and start earning.