Chapter 8

LLMs + RAG

Large language models have transformed what's possible in NLP — and building with them is harder than it looks. This chapter covers the LLM landscape and application patterns (fine-tuning, prompt engineering, RAG, agents), then digs into the practical challenges that dominate real deployments: embedding space visualization and similarity metrics as tools for understanding and debugging, RAG's cascading design decisions, and the Curse of Evaluation.

• 1. What Is a Large Language Model?→
• 1. Visualizing Embedding Spaces→
• 3. Similarity Metrics and the Limits of Cosine→
• 3. Retrieval-Augmented Generation (RAG)→
• 4. The Curse of Evaluation→