Glossary · Generative AI and LLMs
What is NeMo Guardrails? Definition and meaning
A toolkit that adds topic, safety and security rails to LLM applications using a dedicated rule language.
Definition
NeMo Guardrails: A toolkit that adds topic, safety and security rails to LLM applications using a dedicated rule language.
In short: NVIDIA's programmable guardrails for conversational apps.
When it is used
Keeping assistants on topic and safe.
Where it fits
NeMo Guardrails belongs to LLM safety in the Generative AI and LLMs topic. These are the other terms in the same group:
- Guardrails AI: A framework that checks model responses against validators for structure, safety and content rules.
- Presidio: Microsoft's open-source toolkit for finding and anonymizing personally identifiable information in text and images.
- Red-teaming: Systematically testing a model or application with adversarial inputs to find unsafe or unintended behaviour.
Learn more
The full guide to NeMo Guardrails explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.