Monitoring code snippets (external deployments)¶
When you create an external model deployment, you are notified that the deployment requires the use of monitoring snippets to report deployment statistics with the monitoring agent. You can access these monitoring snippets on an external model deployment's Predictions > Monitoring tab. The monitoring snippet is designed to configure your MLOps library to send a model's statistics to DataRobot MLOps and represent those statistics in the deployment. Use this functionality to report back Scoring Code metrics to your deployment.
Navigate to Predictions > Monitoring for your deployment to view the snippet:
| Content | Description | |
|---|---|---|
| 1 | Language | Select the Language for the monitoring code snippet. To monitor Scoring Code with a deployment, select the Java language and copy the snippet to your clipboard. For further instructions, reference the monitoring agent's internal documentation. |
| 2 | Copy to clipboard | Copy the monitoring snippet in the selected language to implement monitoring for an external model deployment. |
| 3 | Download Monitoring Agent | If you have not yet configured the monitoring agent to monitor your deployment, download the MLOps agent tarball. Additional documentation for setting up the monitoring agent is included in the tarball. |
Java requirement
The MLOps monitoring library requires Java 11 or higher. Without monitoring, a model's Scoring Code JAR file requires Java 8 or higher; however, when using the MLOps library to instrument monitoring, a model's Scoring Code JAR file requires Java 11 or higher. For Self-managed AI platform installations, the Java 11 requirement applies to DataRobot v11.0 and higher.