Tutorials

Step-by-step guides for learning PersonaGym.

Tutorial Overview

These tutorials will guide you through the key concepts and workflows of PersonaGym.

Tutorial	Description	Duration
Tutorial 1: Basics	Core concepts and first pipeline run	~15 min
Tutorial 2: Persona Generation	Deep dive into persona system	~20 min
Tutorial 3: Query & Interaction	Query generation and conversations	~25 min
Tutorial 4: Noise Injection	Distractor system configuration	~20 min
Tutorial 5: Advanced Usage	Custom configurations and scaling	~30 min

Prerequisites

Before starting the tutorials:

1. Install PersonaGym following the Installation Guide

2. Configure API keys in .env or config.yaml

3. Verify installation with a test run:

   python run.py --num-personas 1
   

What You’ll Learn

By completing these tutorials, you will:

• Understand the 6-stage pipeline architecture

• Configure personas with custom dimensions

• Generate and adapt queries to personas

• Simulate multi-turn conversations

• Apply semantic noise for model robustness

• Export training data for downstream use

• Scale up generation efficiently

Example Notebooks

For interactive learning, check out the Jupyter notebooks in the notebooks/ directory (if available).

Getting Help

If you encounter issues:

1. Check the Troubleshooting section

2. Review the API Reference

3. Open an issue on GitHub

Let’s Get Started!

Begin with Tutorial 1: Basics to understand the core concepts.