Giskard Library

Giskard Library is a Python package for testing and evaluating AI applications. It provides a solid foundation for developers to ensure quality and reliability in LLM-based systems, RAG applications, and AI agents.

The library is available on GitHub and formed the basis for the Red Teaming LLM Applications course on DeepLearning.AI.

Caution

Giskard v3 is currently in Pre-release (Beta). We are actively refining the APIs and welcome early adopters to provide feedback and report issues as we move toward a stable 3.0.0 release.

The third version of the library is available as a pre-release (Beta). This version is a major rewrite and includes new features such as Checks.

Note

Looking for Giskard v2 features such as RAGET and Scan? They are not available yet in Giskard v3. If you still want to use them, please check the Giskard v2 documentation ↗. We are working to bring them to Giskard v3 as soon as possible! Follow our progress on the v3 roadmap ↗.

Need Help?

• Documentation: Explore the Checks documentation for detailed guides
• Examples: Check our GitHub repository ↗ for more examples
• Community: Join our Discord ↗ for support and discussions
• Enterprise: Ready for team collaboration? Request a trial of Giskard Hub