NeMo Guardrails
Toolkit for adding programmable guardrails to LLM-based conversational AI
About
NeMo Guardrails is an open-source toolkit that allows developers to easily add programmable guardrails to LLM-based conversational applications. It provides a way to control and guide the output of large language models, enhancing safety, reliability, and functionality of AI chatbots and conversational agents
Key features
- INPUT RAILS,
- DIALOG RAILS,
- RETRIEVAL RAILS,
- EXECUTION RAILS, OUTPUT RAILS,
- CUSTOMIZABLE GUARDRAILS,
- MULTI-MODEL SUPPORT,
- COLANG SCRIPTING
Use cases
- SAFETY ENHANCEMENT,
- TOPIC GUIDANCE,
- DETERMINISTIC DIALOGUE FLOWS,
- RAG INTEGRATION,
- CONVERSATIONAL AGENT DEVELOPMENT
