Run an evaluation

This page shows you how to run evaluations for your generative language models and applications with the Gen AI evaluation service.

Before you begin

Before you run evaluations, complete the following prerequisites:

Install the Agent Platform SDK

To install the Gen AI Evaluation module from the Agent Platform SDK for Python, run the following command:

!pip install -q google-cloud-aiplatform[evaluation]

For more information, see Install the Agent Platform SDK for Python.

Authenticate the Agent Platform SDK

After you install the Agent Platform SDK for Python, you need to authenticate. The following topics explain how to authenticate with the Agent Platform SDK if you're working locally and if you're working in Colaboratory:

  • If you're developing locally, set up Application Default Credentials (ADC) in your local environment:

    1. Install the Google Cloud CLI, then initialize it by running the following command:

      gcloud init

    2. Create local authentication credentials for your Google Account:

      gcloud auth application-default