Exam DP-100 topic 4 question 46 discussion

Answer should be 1.create training pipeline 2.create inference pipeline 3.deploy to inference cluster

The correct sequence of actions to ensure that client applications can submit data as HTTP requests and receive predictions as responses is: b) Create a pipeline that trains a classification model and run the pipeline on the compute cluster. You first need to create and run a training pipeline in the Azure Machine Learning Designer. This pipeline should train a classification model on your data. d) Create a real-time inference pipeline and run the pipeline on the compute cluster. After the model is trained, you can create a real-time inference pipeline. This type of pipeline will use your trained model to make predictions on new data in real time. a) Deploy a service to the inference cluster. The last step is to deploy your real-time inference pipeline as a service to the inference cluster. This service will allow client applications to send data as HTTP requests and receive predictions as HTTP responses

Create pipeline that trains classification model -> deploy service to the inference cluster -> create real time inference pipeline