RAG: Retrieval-Augmented Generation as an engineering system

This section builds the engineering foundation for RAG: how text becomes numbers, how retrieval works, why embeddings and transformers matter, and how to think about RAG as a system you can build, measure, and improve.

• Why words turn into numbers: word spaces and features
• Bag of Words and TF–IDF
• Embeddings as continuous spaces of meaning
• Transformers and context: from static vectors to understanding meaning
• Hands-on: embeddings in PHP with transformers (inference, not training)
• RAG: Retrieval-Augmented Generation as an engineering system