Building a RAG system

A hands-on course where you build a working retrieval-augmented generation (RAG) system over veterinary text, then learn to judge whether it gives good answers. It takes about eleven hours, in hosted notebooks, so there is nothing to install.

Who it is for

Veterinary professionals and informatics people who are comfortable with a computer but are not software engineers. You can follow instructions in a notebook and are willing to read a little Python. You do not need a machine learning background.

What you leave with

A working RAG project with test results, and the words to explain it in a job interview.

Start here

The opening module, How LLMs work, is open to everyone. It is shared with Using AI in practice.

The rest of the course

The rest of the course is for AVI members and opens later.

1. Setup and notebook primer, 30 minutes
2. Why RAG exists, 1 hour
3. Documents, chunking, embeddings, 1.5 hours
4. Retrieval, 1.5 hours
5. Generation with citations, 1.5 hours
6. Evaluation, 2 hours
7. Failure modes and safety, 1 hour
8. Capstone and teach back, 2 hours