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
  • How It Works
  • Guardrail Types
  • Supported LLMs
  • Release Notes

Get Started

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

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 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
    • Memory Model Cache
    • KV Cache Reuse
  • Exceptions

Run Guardrailed Inference

  • About Running Guardrailed Inference
  • Python API
    • Overview
    • Core Classes
    • Generation Options
    • Streaming
    • Event-Based API
  • Guardrails API Server
    • Overview
    • Run the Server
    • Chat Completions
    • List Configurations
    • Actions Server

Evaluation

  • Evaluate Guardrails
  • Vulnerability Scanning

Observability

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

More Deployment Options

  • Deployment Options
  • Docker
  • NeMo Microservice

Integration with Third-Party Libraries

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

Reference

  • Architecture
  • Sequence Diagrams
  • Use Case Diagrams
  • Python API
  • CLI
  • Guardrails API Server Endpoints

Troubleshooting

  • Troubleshooting

Resources

  • FAQs
  • Glossary
  • Security
  • 1 Hello World

1 Hello World#

  • Hello World
    • Prerequisites
    • Step 1: create a new guardrails configuration
    • Step 2: load the guardrails configuration
    • Step 3: use the guardrails configuration
    • Step 4: add your first guardrail
    • CLI Chat
    • Server and Chat UI
    • Next
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.