When to Prompt, RAG, or Fine-Tune
Explore how to decide between prompting retrieval-augmented generation (RAG), and fine-tuning when customizing large language models. Understand a hierarchical approach that starts with prompt engineering, moves to RAG for knowledge gaps, and uses fine-tuning for behavior changes. Gain a strategy for efficient and effective LLM application.
We have now explored the three primary methods for controlling and extending a large language model. We know how to guide its behavior with prompts, provide ...