This course breaks down the AI concepts Retrieval Augmented Generation (RAG) and fine-tuning to explain how they factor into building robust enterprise applications.
Overview
Syllabus
Introduction
- RAG, fine-tuning, and the enterprise
- How LLMs work
- Context makes all the difference
- RAG: Retrieval Augmented Generation
- The RAG flow
- Embeddings: Helping AI understand data
- Knowledge graphs
- Fine-tuning
- RAFT: RAG with fine-tuning
- Tying it all together
Taught by
Morten Rand-Hendriksen