Evaluate and Select Best AI Output from Multiple Options

Eval Select Best is a promptfoo example workflow that demonstrates how to set up and run evaluations using promptfoo. It provides a starting configuration that you can customize with your own prompts, test cases, and evaluation criteria.

Use this example when you want a starting point for setting up promptfoo evaluations with a pre-configured example. It's helpful when you're learning how to structure your promptfooconfig.yaml file and want to see a working configuration.

Do NOT use this if you need a different type of evaluation example - promptfoo offers other example templates that may better suit your specific use case. This is a starting template, not a production-ready solution.

You provide your OPENAI_API_KEY environment variable and can edit the promptfooconfig.yaml file to customize the configuration.

You receive evaluation results that can be viewed using the promptfoo view command.

Initialize the example in your environment:

npx promptfoo@latest init --example eval-select-best
cd eval-select-best

Set your OpenAI API key as an environment variable, then edit the promptfooconfig.yaml file to customize your configuration. Run the evaluation:

promptfoo eval

After the evaluation completes, view the results by running promptfoo view.

This example workflow is designed for developers and prompt engineers who want to get started with promptfoo evaluations using a pre-configured example as a foundation for their own testing setup.