Create a Model Snapshot

Owned by Dave Trier
Apr 20, 2021
3 min read

  1. From the Production Model Inventory, open the specific model that you would like to snapshot. Select the “Create Snapshot” button from the top right.

 

2. Optionally, add a Name and Description for the snapshot. Most important, add the same “Model Service Tag” that was added to the requisite Runtimes (see above). This will ensure that the MLC will know the correct Runtimes to which the model should be deployed throughout the life cycle.

  1. Example: add a “cc-fraud” Model Service Tag to the snapshot.

 

3. Optionally suggest the Runtime Type OR the specific Runtimes that will be used by the model during its life cycle, or simply allow the MLC to find the best runtime for the model.

 

4. Optionally add any monitors (called “associated models”)

 

5. Review the Snapshot details. When ready, select “Create Snapshot”.

 

6. The snapshot details page will be opened with all of the details provided during the create snapshot process.

 

7. Additionally, the requisite Model Life Cycle will automatically begin orchestrating all of the steps necessary to operationalize the model. This includes deployment of the model as REST into the designated ModelOp runtimes or the best matching available ModelOp runtime. The details of the model life cycle can be seen in the “Model Life Cycle” section of the snapshot page.

 

8. Note, model life cycle updates and any errors in the model life cycle execution will be populated in the “Notifications” pane of the home page. As well, depending on the environment configuration, Jira and/or ServiceNow tickets may also be raised in the event of an issue. Granular logs can be found in the “MLC Manager” docker logs, which typically are configured to write to ELK or a similar enterprise log aggregation and visualization capability.