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

NVIDIA NeMo Guardrails

NVIDIA NeMo Guardrails - Home NVIDIA NeMo Guardrails - Home

NVIDIA NeMo Guardrails

Table of Contents

NVIDIA NeMo Guardrails

  • About NeMo Guardrails
  • Installation Guide
  • Getting Started
  • Release Notes

Common Tasks

  • Configuration Guide
    • Custom Initialization
    • General Options
    • LLM Configuration
    • Guardrails Configuration
    • Tracing Configuration
    • Knowledge Base
    • Exceptions and Error Handling
  • Guardrails Library
  • Guardrails Process
  • Colang Guide
  • LLM Support
  • Multimodal Data
  • Python API
  • CLI
  • Server Guide
  • LangChain
    • LangChain Integration
    • RunnableRails
    • LangGraph Integration
    • Chain-With-Guardrails
      • Chain with Guardrails
    • Runnable-As-Action
      • Runnable as Action
  • Detailed Logging
    • Output Variables
  • Tracing
    • Quick Start
    • Adapter Configurations
    • Advanced OpenTelemetry Integration
    • Troubleshooting
  • Jailbreak Detection Heuristics
    • Using Jailbreak Detection Heuristics
  • LLMs
    • NVIDIA AI Endpoints
      • Using LLMs hosted on NVIDIA API Catalog
    • Vertex AI
      • Using LLMs hosted on Vertex AI
  • Multi Config API
    • Multi-config API
  • Migrating from Colang 1 to Colang 2

Advanced Uses

  • Generation Options
  • Prompt Customization
  • Embedding Search Providers
  • NeMo Guardrails with Docker
  • Streaming
  • AlignScore Deployment
  • Extract User-provided Values
  • Bot Message Instructions
  • Event-based API
  • Self-hosting Llama Guard using vLLM
  • Nested AsyncIO Loop
  • Vertex AI Setup
  • Nemotron Safety Guard Deployment
  • Llama 3.1 NemoGuard 8B Topic Control Deployment
  • NemoGuard JailbreakDetect Deployment
  • KV Cache Reuse for NemoGuard NIM
  • Blueprint with NemoGuard NIMs
  • Tools Integration with NeMo Guardrails
  • Memory Model Cache
  • Guardrailing Bot Reasoning Content

Security

  • Security Guidelines

Evaluation

  • Guardrails Evaluation
  • LLM Vulnerability Scanning

Guardrails with Colang

  • Hello World
  • Core Colang Concepts
  • Demo Use Case
  • Input Rails
  • Output Rails
  • Topical Rails
  • Retrieval-Augmented Generation

Colang 2.0

  • Overview
  • 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)
      • Fundamental Core Flows (core.co)
      • Timing Flows (timing.co)
      • LLM Flows (llm.co)
      • Interactive Avatar Modality Flows (avatars.co)
      • Guardrail Flows (guardrails.co)
      • User Attention Flows (attention.co)
    • Make use of Large Language Models (LLM)
    • More on Flows
    • Python Actions
    • Development and Debugging

Reference

  • Architecture
    • Architecture Guide
  • Glossary
  • Frequently Asked Questions (FAQ)
  • Evaluation

Evaluation#

  • Guardrails Evaluation
    • Dialog Rails
    • Input and Output Rails
  • LLM Vulnerability Scanning
    • Garak
    • Scan Results
    • LLM Vulnerability Categories
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.