Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Reviewing a model update

Updated on May 17, 2024

Use this endpoint to approve or reject a candidate model in a prediction by using Machine Learning Operations (MLOps).

POST /predictions/model_update/{referenceID}/review

Method
POST
Endpoint
/predictions/model_update/{referenceID}/review
Sample URL
http://IP:PORT/prweb/api/application/v2/predictions/model_update/M-5104/review

{referenceID} is an identifier of a model update that you want to approve or reject, for example, M-5104. A request that starts a model update returns this reference ID. For more information, see Starting a model update.

Request

For example: { "action": "Approve", "review_note": "Approving model for shadow", "shadow_mode": true}

Review request parameters

NameTypeDescription
actionString (Approve, Reject)This parameter allows you to approve a model for deployment to production or to reject the model.
review_noteStringA comment from the data scientist to indicate the reason for the approval or rejection of the model.
shadow_modeBoolean (True, False)True places the model in shadow mode. False replaces the active model in the prediction with this model.

Response

For example: { "message": "referenceID M-5104 is Approved. New status Approved"}

Response parameters

NameTypeDescription
messageStringThe output of the review command.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us