Deploying models
If the model is not autodeployed, then if you are happy with the results, you can now deploy the model.
Before you begin
You only need to perform this task if you generated a model that requires manual deployment.
Procedure
- From the AI Model Management, click the options menu for the algorithm configuration that includes the model that you want to deploy.
- Click Deploy.
Reference information
The following information is referenced in this task.
List of algorithm configurations
| Column | Description |
|---|---|
| Version | Latest version of the model. A new version of the model is generated every time the algorithm configuration is run. |
| Deployed version | Currently deployed version of the model. If training is scheduled and deployment is automatic, then the value in this field always matches the value in the Version field. |
| AI algorithm | The AI algorithm related to this record. Possible values are: Change risk, Log anomaly detection, Similar tickets, and Temporal grouping. |
| Schedule | Displays the schedule frequency (Daily, Weekly, Biweekly, or Monthly). If no schedule was set, then this field displays the text Run manually. |
| Last trained | Date and time this configuration was last run. If it has never been run then this field is blank. |
| Status | Displays one of the following status values: (a) Not started: this configuration has not yet been run; (b) Training: the configuration is currently running; (c) Training queued: training is currently waiting on another training job to complete; (d) Training complete: the most recent configuration ran was successful; (e) Failed: Training failed. |