Skip to main content
Ctrl+K
NVIDIA NeMo Guardrails Toolkit Developer Guide - Home NVIDIA NeMo Guardrails Toolkit Developer Guide - Home

NVIDIA NeMo Guardrails Toolkit Developer Guide

NVIDIA NeMo Guardrails Toolkit Developer Guide - Home NVIDIA NeMo Guardrails Toolkit Developer Guide - Home

NVIDIA NeMo Guardrails Toolkit Developer Guide

Table of Contents

About NeMo Guardrails Toolkit

  • Overview
  • How It Works
    • Rails Overview
    • Rails Sequence Diagrams
    • Detailed Architecture
  • Use Cases
  • Supported LLMs
  • Release Notes

Get Started

  • Installation Guide
  • Tutorials
    • Content Safety
    • Topic Control
    • Jailbreak Detection
    • Multimodal Data

Configure Rails

  • Before Configuring Rails
  • Configuration Overview
  • Core Configuration
    • Model Configuration
    • Guardrails Configuration
      • Built-in Guardrails
    • Prompt Configuration
    • Tracing Configuration
  • Custom Actions
    • Creating Custom Actions
    • Built-in Actions
    • Action Parameters
    • Registering Actions
  • Custom Initialization
    • The Init Function
    • Custom LLM Providers
    • Custom Embedding Providers
    • Custom Configuration Data
  • Colang
    • Colang 2.0 Guide
      • What’s Changed
      • Getting Started
        • Hello World
        • Dialog Rails
        • Multimodal Rails
        • Input Rails
        • Interaction Loop
        • LLM Flows
        • Recommended Next Steps
      • Language Reference
        • Introduction
        • Event Generation & Matching
        • Working with Actions
        • Defining Flows
        • Working with Variables & Expressions
        • Flow control
        • Colang Standard Library (CSL)
        • Make use of Large Language Models (LLM)
        • More on Flows
        • Python Actions
        • Development and Debugging
      • Migrating from Colang 1 to Colang 2
    • Colang 1.0 Guide
      • Colang 1.0 Guide
      • Colang 1.0 Tutorials
        • Hello World
        • Core Colang Concepts
        • Demo Use Case
        • Input Rails
        • Output Rails
        • Topical Rails
        • Retrieval-Augmented Generation
    • Colang Usage Examples
      • Bot Message Instructions
      • Extract User-provided Values
  • Other Configurations
    • Knowledge Base
    • Exceptions and Error Handling

Run Rails

  • Run Rails
  • Core Classes
  • Generation Options
  • Streaming
  • Event-based API
  • Tools Integration

Evaluation

  • Guardrails Evaluation
  • LLM Vulnerability Scanning

Observability

  • Logging
  • Tracing
    • Quick Start
    • Adapter Configurations
    • Advanced OpenTelemetry Integration
    • Troubleshooting

Deployment Guides

  • Deployment Options
  • Local Server Setup
    • Guardrails Server
    • Actions Server
  • Using Docker
  • Using NeMo Guardrails Microservice

Integration with Third-Party Libraries

  • LangChain
    • LangChain Integration
    • RunnableRails
    • LangGraph Integration
    • Chain with Guardrails
    • Runnable as Action
  • Vertex AI
  • AlignScore
  • Llama Guard

Security

  • Security Guidelines

Reference

  • Python API
  • CLI
  • Glossary
  • Frequently Asked Questions (FAQ)
  • Colang Guide
  • Colang 2.0 Guide
  • Language Reference

Language Reference#

This chapter is a comprehensive introduction to Colang. Explaining all important concepts in a bottom up approach.

  • Introduction

  • Event Generation & Matching

  • Working with Actions

  • Defining Flows

  • Working with Variables & Expressions

  • Flow control

  • Colang Standard Library (CSL)

  • Make use of Large Language Models (LLM)

  • More on Flows

  • Python Actions

  • Development and Debugging

previous

Recommended Next Steps

next

Introduction

NVIDIA NVIDIA
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2023-2025, NVIDIA Corporation.