Question

A production Model Serving endpoint currently serves version 7 of a RAG chain registered in Unity Catalog. After deploying version 8, monitoring shows a spike in latency and malformed responses. The team wants to immediately revert live traffic to the known-good version 7 with minimal downtime, while keeping version 8 registered for later debugging. What is the most appropriate action?

Accepted Answer

Update the served entity on the existing endpoint to point to model version 7 (or move the production alias back to version 7), letting the endpoint deploy the reverted version.

Answer

Delete model version 8 from Unity Catalog so the endpoint automatically falls back to version 7.

Answer

Delete the serving endpoint and recreate it from scratch referencing version 7.

Answer

Re-log version 7's chain code as a brand-new registered model and create a separate endpoint for it.