User Guides

• CLI
  • Guardrails CLI
  • Options
• Colang Guide
  • Why a New Language
  • Concepts
  • Syntax
  • Conclusion
• Guardrails Library
  • LLM Self-Checking
  • NVIDIA Models
  • Community Models and Libraries
  • Third-Party APIs
  • Other
• Guardrails Process
  • Overview
  • Categories of Rails
  • The Guardrails Process
  • The Dialog Rails Flow
• LLM Support
  • Evaluation experiments
  • LLM Support and Guidance
• Python API
  • Basic usage
  • RailsConfig
  • Message Generation
  • Actions
  • Action Parameters
• Server Guide
  • Guardrails Server
  • Actions Server
• Advanced
  • AlignScore Deployment
  • Bot Message Instructions
  • Embedding Search Providers
  • Event-based API
  • Extract User-provided Values
  • Generation Options
  • Jailbreak Detection Deployment
  • Self-hosting Llama Guard using vLLM
  • Nested AsyncIO Loop
  • Prompt Customization
  • Streaming
  • NeMo Guardrails with Docker
  • Vertex AI Setup
  • Llama 3.1 NemoGuard 8B ContentSafety Deployment
  • Llama 3.1 NemoGuard 8B Topic Control Deployment
  • Blueprint with NemoGuard NIMs
• Detailed Logging
  • Output Variables
• Input Output Rails Only
  • Generation Options - Using only Input and Output Rails
• Jailbreak Detection Heuristics
  • Using Jailbreak Detection Heuristics
• LangChain
  • LangChain Integration
  • RunnableRails
  • Chain-With-Guardrails
  • Runnable-As-Action
• LLMs
  • NVIDIA AI Endpoints
  • Vertex AI
• Multi Config API
  • Multi-config API