Skip to content

ML Generator from Database Metadata

This guide shows the end-to-end flow for creating ML training DSL artifacts from database metadata, executing training, reviewing persisted versions in ML Generator View, and reusing them in DATAMIMIC DSL.

Prerequisites

  1. Configure a database environment in Environments.
  2. In the environment row, open More actions (⋯), select Refresh metadata snapshot, and confirm the Scan Database Metadata dialog.
  3. Open Database View and ensure your tables/columns are available.

1. Build an ML training artifact in Database View

  1. In Database workbench → Planning, select your scope.
  2. Run Plan subset (preset-based closure + relationship validation).
  3. Verify preflight state.
  4. In Generate artifacts, click Configure model, then select ML training model in the wizard that opens.
  5. Set naming options and create the model artifact.
  6. Execute the generated DSL model (with <ml-train> nodes) to start training and persist model versions.

For planning and scope details, see Auto-Generate Model from Database.

Note

Training duration depends on table size, feature complexity, and selected runtime. Larger training workloads can require more CPU/RAM and, depending on environment setup, GPU resources (for example NVIDIA cards).

2. Inspect trained model quality and versions in ML Generator View

Open ML-Gen from the top navigation.

Only models with completed/persisted training runs are listed with versions and statistics in this view.

You can:

  • search and select generators in the left pane,
  • switch versions in the version list,
  • set default version,
  • delete outdated versions,
  • inspect status, utility/privacy KPIs, and top drift indicators,
  • Download report for the HTML quality-assurance report.
ML Generator View
ML Generator View: model quality overview, version selection, and version actions

3. Reuse ML generators in DATAMIMIC DSL

After training and approving a model version, follow the EE-owned ml-train reference for the verified DSL syntax. The Platform contributes the approved model identifier through the project workflow.

DATAMIMIC DSL using ML generators
Simple Mode: generate nodes read the approved models as ml:// sources

Operational Notes

  • Use stable subset planning inputs for reproducible training behavior.
  • Keep one validated default version per generator for downstream DSL use.
  • Retrain when schema drift or data distribution changes materially.
  • Review utility/privacy status before promoting a version to default.
  • Treat generated recommendations and models as baseline output that still requires project-specific tuning.