mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2025-10-09 13:40:09 +03:00
c69bc5d4e6
* feat: Add optional curriculum support to dataset registration and creation * docs: Add docstrings to create_curriculum() and register_dataset() * feat: Add curriculum configuration classes for CurriculumExperiment * feat: Add weight parameter to CurriculumAttributeConfig and use in DatasetSpec * refactor: Simplify CurriculumAttributeConfig with "*" attribute level support * test: Add unit tests for CurriculumExperiment class * feat: Add from_yaml() method to CurriculumExperimentConfig with unit test
Reasoning Gym Tools
This directory contains additional tools for working with Reasoning Gym:
Server
A FastAPI server that manages reasoning gym experiments, allowing runtime configuration and monitoring.
Starting the Server
- Install server dependencies:
pip install -e ".[server]"
- Set the API key environment variable:
export REASONING_GYM_API_KEY=your-secret-key
- Start the server:
uvicorn tools.server.server:app
The server will be available at http://localhost:8000. You can access the API documentation at http://localhost:8000/docs.
RGC (Reasoning Gym Client)
A command-line interface for interacting with the Reasoning Gym server.
Installation
pip install -e ".[cli]"
Usage
First, set the API key to match your server:
export REASONING_GYM_API_KEY=your-secret-key
Then you can use the CLI:
# List all commands
rgc --help
# List experiments
rgc experiments list
# Create a new experiment interactively
rgc experiments create my-experiment
# Create from config file
rgc experiments create my-experiment -f config.yaml
# Show experiment details
rgc experiments show my-experiment
# Edit dataset configuration
rgc config edit my-experiment chain_sum
Example Configuration File
Here's an example config.yaml for creating an experiment:
size: 500
seed: 42
datasets:
chain_sum:
weight: 1.0
config:
min_terms: 2
max_terms: 4
min_digits: 1
max_digits: 2
allow_negation: false