Get started with Gemini Enterprise Agent Platform Experiments: Notebook

This tutorial demonstrates how to use Gemini Enterprise Agent Platform in production and covers getting started with Vertex AI Experiments.

Notebook: Get started with Vertex AI Experiments

To see an example of getting started with Vertex AI Experiments, run the "Get started with Experiments" notebook in one of the following environments:

Open in Colab | Open in Colab Enterprise | Open in Vertex AI Workbench | View on GitHub

This tutorial uses the following Google Cloud ML services:

• Vertex AI Experiments
• Vertex ML Metadata
• Gemini Enterprise Agent Platform training

The steps performed include:

• Local (notebook) training
  • Create an experiment.
  • Create a first run in the experiment.
  • Log parameters and metrics.
  • Create artifact lineage.
  • Visualize the experiment results.
  • Execute a second run.
  • Compare the two runs in the experiment.
• Cloud (Agent Platform) training
  • Within the training script:
    • Create an experiment.
    • Log parameters and metrics.
    • Create artifact lineage.
  • Create a Gemini Enterprise Agent Platform training custom job.
  • Execute the custom job.
  • Visualize the experiment results.

Relevant content

• Introduction to Vertex AI Experiments