Example Projects and Cookbooks

Optimizer Introduction Cookbook

Quick example notebook using HotPotQA dataset

This example demonstrates end-to-end prompt optimization on the HotPotQA dataset using Opik Agent Optimizer. All steps, code, and explanations are provided in the interactive Colab notebook below.

Load Example Notebook

To follow this example, simply open the Colab notebook below. You can run, modify, and experiment with the workflow directly in your browser—no local setup required.

PlatformLaunch Link
Google Colab (Preferred)Open in Colab
AlternativesOpen in GitHub Codespaces Open in Deepnote

What you’ll learn

  • How to set up Opik Agent Optimizer SDK
  • How to setup Opik Cloud (Comet Account) for prompt optimization
  • How to use the HotPotQA dataset for multi-hop question answering
  • How to define metrics and task configs
  • How to run the FewShotBayesianOptimizer and interpret results
  • How to visualize optimization runs in the Opik UI

Quick Start

  1. Click the Colab badge above to launch the notebook.
  2. Follow the step-by-step instructions in the notebook.
  3. For more details, see the Opik Agent Optimizer documentation.