​

Reward Kit Documentation

Welcome to the Reward Kit documentation. This guide will help you create, test, and deploy reward functions for evaluating and optimizing LLM responses.

​

Getting Started

​

Developer Guide

• Getting Started with Reward Functions: Learn the basics of reward functions.
• Reward Function Anatomy: Understand the structure of reward functions.
• Core Data Types: Explore the data models used in reward functions.
• Evaluation Workflows: Learn the complete lifecycle from development to deployment.
• Dataset Configuration Guide: Understand how to configure datasets using YAML.
• Hydra Configuration for Examples: Learn how Hydra is used for configuration in examples.
• Integrating with Braintrust: Bridge Reward Kit with the Braintrust SDK.

​

Examples

• Examples Overview: Browse available examples and learn how to run them. The primary documentation for each example is its own README.md in the examples/ directory.

​

Tutorials

• Creating Your First Reward Function: Step-by-step guide to creating a reward function

​

API Reference

• API Overview
• RewardFunction Class
• Reward Function Decorator
• Data Models

​

Command Line Interface

• CLI Overview

​

Community and Support

• GitHub Issues: Report bugs and request features
• Contributing Guide: How to contribute to the Reward Kit project