mattbit / giskard-doc

Giskard public documentation on GitBook 📗

description
Open-Source & Collaborative Quality Assurance for AI models

Get started with Giskard

Giskard creates interfaces for humans to inspect & test AI models. It is open-source and self-hosted.

Giskard lets you instantly see your model's prediction for a given set of feature values. You can set the values directly in Giskard and see the prediction change.

Saw anything strange? Leave feedback directly within Giskard, so that your team can explore the query that generated the faulty result. Designed for both tech and business users, Giskard is super intuitive to use! 👌

Want to ensure your model is right? Giskard enables you to turn your business feedback into actionable tests. Create in a few clicks automatic tests and execute them in your CI/CD pipeline each time, you create a new version of your model. 🐢

And of course, Giskard works with any model, any environment and integrates seemlessly with your favorite tools ⤵️

Workflow

1. Validate your ML model by collecting feedback

Collect feedback of your ML models

2. Discuss and analyse feedback

3. Turn feedback into tests

Write some custom tests

4. Check your test result

Test dashboard

5. Deploy your tests in your CI/CD pipeline

Have your tests executed in your CI/CD pipeline

Guides: Jump right in

Follow our handy guides to get started on the basics as quickly as possible:

{% content-ref url="guides/installation/" %} installation {% endcontent-ref %}

{% content-ref url="guides/upload-your-model/" %} upload-your-model {% endcontent-ref %}

{% content-ref url="guides/review-your-model.md" %} review-your-model.md {% endcontent-ref %}

{% content-ref url="guides/create-tests-from-your-review/" %} create-tests-from-your-review {% endcontent-ref %}

License

This project is licensed under the terms of the Apache Software License 2.0 license. See LICENSE for more details.