Skip to content

1. Learning Objectives

GENAIOPS: Deployment is part of the Production stage. (click to view figure)

GenAIOps toolchain

In the previous sections we completed model selection, exploration and customization:

  • We learned to use the model catalog and benchmarks to "select" a model
  • We learned to use model deployment and chat playground to "explore" the model
  • We learned to add search services and data to "ground" responses with RAG

We can test the grounded model in the playground, but now we want to get a sense for what a real-world user experience and interaction looks like. Let's deploy the grounded chat model to Azure, then add a web app to interact with it! This is what model integration for real-world use, looks like.

By the end of this section you should know how to:

  • Deploy ground chat prototype as a hosted endpoint (chat API)
  • Deploy a web based application to interact with it (chat UI)
  • Use the deployed application (with history) or update it