v1.36

Release notes

We are pleased to announce the release of v1.36.0, which includes several new features, improvements, and bug fixes. Please note that this release can contain breaking changes.

⚠️ Breaking changes

• Creating and updating Sagemaker Deployments api endpoints changed. From /workspaces/{workspaceId}/deployments to /workspaces/{workspaceId}/deployments/sagemaker. See Swagger for more information.

✨ New features

• Standard Explainer
  For XGBoost and Scikit learn tree based models it is possible to include a Standard Explainer (Tree SHAP). This will provide your Deployment with explainability without having to train an explainer yourself.

• OIDC Integration (Enterprise only)
  For enterprise installations an OIDC authentication method option has been added for both Microsoft and Google accounts, allowing you to log in to Deeploy without having to create an account.

• Add support for custom Deployment metadata keys
  Adding custom fields in your Deployment metadata will now be visible in the model details page.

🛠️ Improvements

• Improved Deployment live events stability
• Add indicator for the number of Deployments in overview
• Added a warning to select additional resources for Pytorch & TensorFlow models

🐛 Bug fixes

• Fixed Azure Blob storage delete files issue
• Fixed Disagreement ratio graph showing wrongly labeled classes
• Fixed broken state when a repository, branch or commit was deleted for active Deployment
• Fixed credentials issue in Deployment detail page
• Fixed issues with unsaved changes confirm dialog
• Fixed the actuals code snippets