Artificial Intelligence
← Back All series →

RAG & Grounding LLMs

4 chapters · 35 min total

How to ground a language model in your own data — deciding between fine-tuning, prompt engineering and retrieval, understanding what RAG is, how vector databases make semantic search possible, and the real decisions involved in building a production RAG pipeline.

  1. 01 Fine-Tuning vs Prompt Engineering vs RAG — Which to Use 8 min read
  2. 02 RAG — Retrieval Augmented Generation Explained 9 min read
  3. 03 Vector Databases Explained — How Semantic Search Works 8 min read
  4. 04 Building a RAG Pipeline — The Decisions That Actually Matter 10 min read
Start Series — Chapter 1 →