RAG in 60 Minutes

4 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

1. 1

   Let the AI read your documents

   A model does not know your documents. RAG finds the relevant pieces and hands them to the model, so its answers come from your documents and say where.

2. 2

   Find the right chunks by meaning

   Each chunk becomes a point on a map of meaning. A question becomes another point, and retrieval picks the chunks nearest to it.

3. 3

   Answer only from the documents

   Hand the chunks you found to the model and tell it to answer only from them, so the answer comes from your documents and not from the model's memory.

4. 4

   Show the sources and run the whole thing

   A grounded answer becomes one people can trust when it names a source for every fact, shows how confident it is, and admits when it does not know. Then you run the whole pipeline yourself.

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

• You answer 6 short questions, one for each module, in your own words (at least 40 words each).
• An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
• To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

1. Module 1, What is RAG?: Understanding retrieval-augmented generation.
2. Module 2, Upload & Chunk: Document splitting with overlap.
3. Module 3, Embed & Store: Vector embeddings in pgvector.
4. Module 4, Search & Retrieve: Semantic search with relevance scoring.
5. Module 5, Generate Answers: LLM answers grounded in your docs.
6. Module 6, Add Citations: Source attribution and confidence scores.

What you walk away with