Free RAG course
Build retrieval-augmented generation step by step: embeddings, chunking, vector search, grounded answers with sources, and the measurements that tell you whether it works.
Create a free account Try the first lesson
What you'll be able to do
- Explain the three steps of RAG: index, retrieve, generate
- Turn text into embeddings, and measure how similar two texts are with cosine similarity
- Split long documents into chunks that keep their source and position
- Build a small vector store with search, filtering and delete
- Write a working RAG function that returns an answer and its sources
- Combine keyword and embedding search, and measure retrieval with hit rate and MRR
- Reduce hallucination, and flag numbers and quotes an answer can't back up
Who it's for
For developers who want a model to answer from their own documents instead of its memory, and who want to understand each part before reaching for a framework.
Before you start
Some lessons here build on earlier ones in the academy. The placement test can mark off what you already know, and you can open any of them first:
New to Python? Start with the free Python for AI course.
The 13 lessons
One is free with no account, and a free account opens the rest.
- What an LLM actually does FreeNext-token prediction, and why that produces useful behavior.
- Tokens and the context windowHow text becomes tokens, and what fits in one request.
- Prompt fundamentalsClear instructions, context and constraints: the 80% of prompting.
- System prompts and rolesSet behavior once, separately from the conversation.
- EmbeddingsMeaning as a list of numbers, so text can be compared.
- Similarity searchFind the most relevant text by comparing embeddings.
- Chunking documentsSplit long documents so the right piece can be retrieved.
- Vector databasesStore and search millions of embeddings quickly.
- Retrieval-augmented generationAnswer from your own documents instead of the model's memory.
- Making RAG goodHybrid search, reranking and citations.
- Hallucinations and groundingWhy models make things up, and how to design against it.
- EvalsMeasure output quality with test sets instead of vibes.
- LLM-as-judgeGrade open-ended output with rubrics and a second model.
When you finish
Finish every lesson, or show you know it in the placement test, and you earn a certificate of completion, "RAG course", with its own link you can share or add to LinkedIn.
Questions
- Is it really free?
- Yes. There's nothing to pay, here or anywhere in the academy. A free account saves your progress and issues your certificate.
- Do I need to install anything?
- No. The Python in these lessons runs in your browser.
- How long does it take?
- About 7 hours in all, at your own pace. Your progress stays where you left it.
- What does the certificate show?
- That your account recorded every lesson as finished or known. It's a certificate of completion from Index Ai Academy, not an accredited qualification.
Start the course
A free account saves your progress across devices and issues your certificate when you finish.