Welcome to RAI Documentation!

RAI is a python library that is written to help AI developers in various aspects of responsible AI development. It consists of a core API and a corresponding web-based dashboard application. RAI can easily be integrated into AI development projects and measures various metrics for an AI project during each phase of AI development, from data quality assessment to model selection based on performance, fairness and robustness criteria. In addition, it provides interactive tools and visualizations to understand and explain AI models and provides a generic framework to perform various types of analysis including adversarial robustness.

Note:

The dashboard GUI is currently designed around 1920x1080 displays

User Guide:

• Introduction
• Getting Started
• Installation
  • Windows 10
  • Install a package locally and run.
• Responsible AI development in RAI
  • Basic Explainability
  • Performance
  • Fairness
• Robustness of AI
• Model Selection
• Demo Cases
• Dashboard
  • RAI Dashboard features
  • How To Run RAI Dashboard
  • Interaction of RAI Dashboard
• Basic component of RAI Design
  • AISystem
  • Certificates
  • Metrics
  • Analysis
• Contribute and Extend RAI
  • Adding Metric Group
  • Adding Certificates
  • Adding Analysis
• Contribution of users to expand its features
  • Contributing to RAI
  • Report bugs using Github’s Issues

Reference Class

• RAI
  • RAI.AISystem
  • RAI.Analysis
  • RAI.certificates
  • RAI.metrics