🔴 Live MLOps Podcast – Building, Deploying and Monitoring Large Language Models with Jinen Setpal
The MLOps Podcast
00:00
Retrieval Augmented Generation Models and Customization Approaches
The chapter explores the structure and capabilities of retrieval augmented generation (RAG) models and how they can adapt to generate responses. It discusses the counterintuitive aspects of working with large language models (LLMs) and compares prompt engineering and fine tuning for customization. The chapter also addresses the decision criteria for choosing between prompt engineering and fine tuning based on the production domain.
Transcript
Play full episode
