Python
Retrieval-Augmented Generation (RAG) with Python
Build a complete RAG pipeline from scratch in 8 steps: collecting documents, chunking, embedding, vector storage, embedding a query, retrieval, augmentation, and generating a grounded LLM response. You'll write real, runnable Python for every step, no API key required until the very last one.
9 lessons
Start the first lessonCurriculum
- 1Data Collection📝 quiz
- 2Data Chunking📝 quiz
- 3Embedding📝 quiz
- 4Vector Storage📝 quiz
- 5Query Input📝 quiz
- 6Retrieval📝 quiz
- 7Augmentation📝 quiz
- 8LLM Response📝 quiz
- 9Final Project: Build Your Own Mini RAG Pipeline
Every lesson is open, take them in order or jump straight to what you need.