reward-kit

library0.4.1pypypi✓ verified 87d ago

A Python library for defining, testing, and using reward functions, particularly for RLHF and AI alignment. Version 0.4.1, pre-1.0, active development with weekly releases.

ai-ml llm-agents

pip install reward-kit

github ↗package ↗

INSTALL

IMPORT

SIG · REWARD-KIT

reward-kit

ai-mlpythonv0.4.1

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

RewardFunction

✓ from reward_kit import RewardFunction

✗ from reward_kit.core import RewardFunction

In version 0.3+ RewardFunction moved to top-level

evaluate_reward

✓ from reward_kit import evaluate_reward

✗ from reward_kit.utils import evaluate_reward

API changed in 0.4.0

Initialize a reward function, load a dataset, and evaluate a sample.

from reward_kit import RewardFunction from reward_kit.data import MoralityQA import os # Use your own API key or prompt key api_key = os.environ.get('REWARD_KIT_API_KEY', 'your-key-here') reward_fn = RewardFunction(model='morality', api_key=api_key) dataset = MoralityQA() score = reward_fn.evaluate(dataset[0]) print(score)

Debug

Known issues

breakingIn version 0.4.0, the evaluate_reward function was moved from reward_kit.utils to top-level reward_kit. Old imports will break.

fix

Use 'from reward_kit import evaluate_reward' instead of 'from reward_kit.utils import evaluate_reward'

affects: >=0.4.0,<0.5

breakingThe RewardFunction class constructor 'model' parameter changed from string to enum in 0.4.1. Strings still work but are deprecated.

fix

Pass a Model enum value, e.g., reward_kit.Model.MORALITY, or keep string but expect future removal.

affects: >=0.4.1

deprecatedThe 'morality' model name is deprecated in favor of 'morality_v2' as of 0.4.0. The v1 model will be removed in 0.5.

fix

Use model='morality_v2' or reward_kit.Model.MORALITY_V2.

affects: >=0.4.0

gotchaBy default, reward functions require an internet connection to call remote APIs. Offline mode is not yet supported.

fix

Ensure you have internet access or expect ConnectionError.

affects: all

Errors

Common errors & fixes

ModuleNotFoundError: No module named 'reward_kit'

Library not installed or installed in wrong environment.

fix

Run 'pip install reward-kit' in the correct Python environment.

AttributeError: module 'reward_kit' has no attribute 'evaluate_reward'

Import path changed in version 0.4.0.

fix

Use 'from reward_kit import evaluate_reward' instead of 'from reward_kit.utils import evaluate_reward'.

ValueError: Unknown model: 'morality'

Model name 'morality' is deprecated in 0.4.0+ and removed in some versions.

fix

Use 'morality_v2' or import Model enum: reward_kit.Model.MORALITY_V2.

Upgrade

Version history

0.4.1latest on PyPI · released Jul 13, 2025

Audit

Dependencies

torchrequiredRequired for tensor operations in reward functions

Agent activity

21 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/fireworks-ai/reward-kit ↗

packagehttps://pypi.org/project/reward-kit/ ↗