© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2024
A. KansalBuilding Generative AI-Powered Appshttps://doi.org/10.1007/979-8-8688-0205-8_5

5. Finetuning: The Theory

Aarushi Kansal1  
Melbourne, Australia

In Chapter 4, you learned about making your LLM-powered application safer and more controllable. In particular, you focused on using NeMo to build guardrails around ensuring your LLM stays on topic, executes the right flow, and is able to block users. You looked into NeMo and understood how it combines LLMs, Colang, and embedding models to create a generalized set of rules, based on natural language rules you give it.

The last few chapters all involve using a foundational model as the “brain” of your application, ...

Get Building Generative AI-Powered Apps: A Hands-on Guide for Developers now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.