Visitor-center comment scoring always runs a tokenizer/featurizer container and then a model container on the same request. The agency wants one endpoint, not two hops the app team must glue together. Which deployment fits?
Select an answer to reveal the explanation.
Short Explanation
Comment scoring always runs tokenizer then model on the same request. A multi-container serial pipeline keeps both on one endpoint. That is not a multi-model endpoint, Personalize is not that pipeline, and two app-glued hops miss the ask.
Full Explanation
A multi-container or serial inference pipeline keeps two serving steps on the same endpoint for one request. That is not a multi-model endpoint (many models, one container pattern). Personalize is not that pipeline, and two app-glued hops miss the ask.