For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Copy to LLMGithubGo to App
DocumentationIntegrationsAgent OptimizationSelf-hosting OpikSDK & API referenceOpik University
DocumentationIntegrationsAgent OptimizationSelf-hosting OpikSDK & API referenceOpik University
  • Getting Started
    • Opik Agent Optimizer
    • Optimization Studio
    • Quickstart
    • Quickstart notebook
    • FAQ
    • Changelog
    • Known Issues
  • Optimization
    • Concepts
    • Configure LLM Providers
    • Define datasets
    • Define metrics
    • Optimize prompts
    • Optimize tools (MCP)
    • Optimize agents
    • Optimize multimodal
    • Dashboard results
  • Optimization Algorithms
    • Overview
    • Benchmarks
    • MetaPrompt
    • HRPO
    • Few-Shot Bayesian
    • Evolutionary
    • GEPA
    • Parameter
    • Tool Optimization
  • Cookbooks & Tutorials
    • Optimizer introduction
    • Synthetic data optimizer
    • ARC-AGI tutorial
    • Multimodal agent tutorial
  • Advanced Topics
    • Extending optimizers
    • Custom metrics
    • Custom optimizer prompts
    • Sampling controls
    • Multiple completions (n)
    • Chaining optimizers
    • API Reference
LogoLogo
Copy to LLMGithubGo to App
On this page
  • Launch the example
  • What this example covers
  • Where the full implementation lives
  • Next steps
Cookbooks & Tutorials

Synthetic Data Optimizer Cookbook

Advanced example notebook using synthetic datasets
Was this page helpful?
Previous

ARC-AGI Optimization Tutorial

Tutorial example using ARC-AGI style code tasks

Next
Built with

This page is a high-level entry point for the synthetic data workflow. Use the notebook or SDK script to run the full example end-to-end.

Launch the example

The notebook is the fastest way to explore synthetic data optimization in your browser.

PlatformLaunch Link
Google Colab (Preferred)Open in Colab
GitHubView the notebook on GitHub

What this example covers

  • Generating synthetic Q&A datasets from Opik traces
  • Using TinyQA (via tinyqabenchmarkpp) and variants like TinyQA++
  • Optimizing prompts with MetaPrompt on synthetic data
  • Reviewing results in the Opik UI

Where the full implementation lives

Notebook: sdks/opik_optimizer/notebooks/OpikSyntheticDataOptimizer.ipynb

SDK codebase: browse sdks/opik_optimizer/ for dataset utilities, metrics, and optimizer implementations.

Next steps

  • Run the notebook and swap in your own traces or datasets.
  • Explore Define datasets and Define metrics for deeper control.