Quality Assurance for AI
Giskard is an open-source quality assurance platform for AI models.
- Inspect ML models visually from your Python notebook π
- Review ML models collaboratively to get feedback on potential errors π§
- Test ML models automatically for a safe deployment to production β
Installation
git clone https://github.com/Giskard-AI/giskard.git
cd giskard
docker-compose up -d
After the application is started you can access at:
login / password: admin / admin
Requirements
Quick Start
You can upload models to Giskard from Jupyter notebooks or any other python environment. it can be done using Giskard client library
There's a demo python notebook available at http://localhost:18888 that can be used to upload a first model.
Documentation
Find out more about Giskard by reading our docs
Community
Join our community on Discord to get support and leave feedback