[RMP] Support individual Vertex AI tools (like feature store) for serving recs with Merlin

[viswa-nvidia]

Problem:

As a current Vertex AI user, I want to use the managed tools provided by Vertex AI instead of running my own real-time services for model serving, such as a feature store, ANN engine, model registry, or Triton server.

Goal:

• Produce a notebook with an example of building a Systems ensemble using Vertex AI operators and deploy to Vertex AI Prediction.

Constraints:

• Getting access to a GCP project.

More research is needed in order to identify further constraints.

Starting Point:

• Provide operators to integrate with the Vertex AI tools for serving:

  • Feature Store
  • Matching Engine (ANN service)
  • Model Registry

• Create an example demonstrating how Merlin works within the Vertex ecosystem

• Add documentation for best practices of Vertex+Merlin

[viswa-nvidia]

James to discuss with Karl on the definition.