RAG: giving AI your own data

Build the single most employable thing in this course.

1. Why RAG exists Say what problem retrieval solves that a bigger model does not.
2. Chunking documents Split a document so retrieved pieces are actually answerable.
3. Vector databases and similarity search Store embeddings and retrieve the nearest ones to a query.
4. Build a document Q&A app Ship a working app that answers questions about your own PDFs.
5. RAG vs fine-tuning: which one do you need? Choose correctly between retrieval and fine-tuning for a given problem.

Ends with a graded checkpoint: 8 questions, pass mark 70%.