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

NVIDIA NeMo Guardrails Library Developer Guide

  • GitHub
  • PyPI
NVIDIA NeMo Guardrails Library Developer Guide - Home NVIDIA NeMo Guardrails Library Developer Guide - Home

NVIDIA NeMo Guardrails Library Developer Guide

  • GitHub
  • PyPI

Table of Contents

About NeMo Guardrails Library

  • Overview
  • Guardrail Types
  • How It Works
    • Sequence Diagrams
    • Architecture
  • Supported LLMs
  • Release Notes

Get Started

  • Install
  • Tutorials
    • Check Harmful Content
    • Content Safety Reasoning
    • Restrict Topics
    • Detect Jailbreak Attempts
    • Add Multimodal Content Safety
  • Integrate

Configure Guardrails

  • About Configuring Guardrails
  • Overview
  • Prerequisites
  • Configuring YAML File
    • Models
    • Guardrails Configuration
    • Prompts
    • Tracing
    • Streaming
      • Streaming LLM Responses
      • Output Rail Streaming
  • YAML Schema Reference
  • Guardrail Catalog
  • Custom Actions
    • Creating Custom Actions
    • Built-in Actions
    • Action Parameters
    • Registering Actions
  • Custom Initialization
    • Init Function
    • LLM Providers
    • Embedding Providers
    • Custom 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 Language Syntax
      • Colang 1.0 Tutorials
        • Hello World
        • Core Colang Concepts
        • Demo Use Case
        • Input Rails
        • Output Rails
        • Topical Rails
        • Retrieval-Augmented Generation
      • Guardrailing Bot Reasoning Content
    • Colang Usage Examples
      • Bot Message Instructions
      • Extract User-provided Values
  • Other Configurations
    • Knowledge Base
    • Embedding Search Providers
  • Caching Instructions and Prompts
    • Memory Model Cache
    • KV Cache Reuse for NemoGuard NIM
  • Exceptions and Error Handling

Run Guardrailed Inference

  • Run Rails
  • Core Classes
  • Generation Options
  • Streaming
  • Event-Based API

Evaluation

  • Evaluate
  • Vulnerability Scanning

Observability

  • Logging
  • Tracing
    • Quick Start
    • Adapters
    • OpenTelemetry
    • Troubleshooting

Deployment Guides

  • Deploy
  • Local Server
    • Guardrails Server
    • Actions Server
  • Docker
  • Microservice

Integration with Third-Party Libraries

  • LangChain Frameworks
    • LangChain Integration
    • RunnableRails
    • Chain with Guardrails
    • Runnable as Action
    • LangGraph
  • Tools Integration

Troubleshooting

  • Troubleshooting

Resources

  • Frequently Asked Questions (FAQ)
  • Python API
  • CLI
  • Use Case Diagrams
  • Glossary
  • Security
  • Colang Guide
  • Colang 2.0 Guide
  • Getting Started
  • Recommended Next Steps

Recommended Next Steps#

The Colang 2.0 getting started guide introduces you to a basic Hello World example, and then goes into Dialog Rails, Input Rails, Multimodal Rails, and other Colang 2.0 concepts like Interaction Loop and LLM Flows.

This only scratches the surface of what can be achieved with Colang 2.0.

If you are an experienced developer and want to learn about the syntax and various features in details, we recommend going through the Language Reference documentation.

Version 0.10.0 of NeMo Guardrails will add more examples including RAG and agents. Also it will bring support for the Guardrails Library, which will enable you to use any of the existing guardrails similar to Colang 1.0.

previous

LLM Flows

next

Language Reference

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

Copyright © 2023-2026, NVIDIA Corporation.