Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Elevating LLM Safety with NVIDIA NeMo Guardrails

via CodeSignal

Overview

This course provides a foundational introduction to NVIDIA NeMo and Colang. You will learn to create basic configuration files, define simple conversation flows using Colang, and perform interactive testing via Python. By the end of this course, you will be familiar with NeMo’s core capabilities and the integration of guardrail policies into your projects.

Syllabus

  • Unit 1: Introduction to NeMo and Colang
    • Crafting Conversational Bot Flows
    • Adding Multiple Allowed Responses
    • Expanding Upon Conversation Flows
    • Creating an Unbooking Flow
    • Writing a Movie Planner Bot Rail from Scratch
  • Unit 2: Adding Input Rails
    • Fixing the Input Rail
    • Updating Input Guidelines
    • Security through Obscurity
    • Ensuring Pirate Speech
    • Adding a Language Guardrail
  • Unit 3: Adding Output Rails and Subflows
    • Guard Your Model Outputs
    • Fixing the Output Rail
    • Adding a Subflow
    • Creating a Looping Subflow
  • Unit 4: Adding Topical Rails
    • Writing Topical Rails
    • Adding General Instructions
    • Adding Sample Conversations

Reviews

Start your review of Elevating LLM Safety with NVIDIA NeMo Guardrails

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.