Monitoring ML models allows you to detect outliers easily and understand which ones are critical, threat or otherwise. It also allows to take immediate action with alerts. Get alerted for a wide range of issues and manage your model’s unique needs, build trustworthy and explainable AI solutions.
- To access ML Monitor, Click on ML Monitor tab on the left navigation bar.
3. To add ML Monitor, Click Add ML Monitor button.
4. Select specific AI Usecase for which you are planning to work, select the related ML Model, ML Docker registry, ML deployment. In item type select the type of ML Monitor you want to create. Select item name in which you have to write the name of the relevant ML Monitor. Then you need to select the assignee, who will approve your ML Monitor.
After creating ML Monitor, it will go to Task Pending of the assigned Approver. The assigned Approver has to go to his list of Task Pending for Approving or Rejecting the request. Both the Assignor and the Approver can track the status of the same task from their respective Task Pending page.
Below are the details of the process step by step -
- Approver firstly needs to click on the specific Task Name. Here Approver will get the details related to task in the Task Brief, he can also see the relevant documents attached for that usecase and can also comment on the task.
- After that, Approver can click the Approve button. Then Approver will need to fill the form. He can also assign the ML Monitor to other team member.
- Then Approver can click on Approve button if he wants to approve. To reject, he can click on Reject button. He can also click on Request to Probyto, if he wants Probyto to work on that task.
Then Select the Due date, it is a kind of expiry date of your ML Monitor. Then click on Create button.
5. After adding ML Monitor, you will see all the ML monitors you have added on the home screen of ML monitor with its title, Usecase ID, ML Model, activation status etc. as shown in the below picture.
6. To edit or configure ML Monitor, Click on the name of any ML Monitor.
7. On the second Level page of ML Monitor You will find Configure, Click on Configure.
- Fill all the details such as-
- Enter the Key- In this column, you need to provide configurations for successful integrations.
- Enter the Value-In this option, you need to give the detail or the link related to your Key.
Then click Submit.
After adding all the configurations, it will be shown below the description of MLMonitor.
- To edit ML Models, Click Edit ML Monitor.
Fill all the relevant details, click Update.