Skip to main content

Build dashboards with the MLflow Search API

You can pull aggregate metrics on your MLflow runs using the mlflow.search_runs API and display them in a dashboard. Regularly such reviewing metrics can provide insight into your progress and productivity. For example, you can track improvement of a goal metric like revenue or accuracy over time, across many runs and/or experiments.

This notebook demonstrates how to build the following custom dashboard using the mlflow.search_runs API:

Search API Dashboard

You can either run the notebook on your own experiments or against autogenerated mock experiment data.

Dashboard comparing MLflow runs notebook

Open notebook in new tab
Was this article helpful?