Metadata-Version: 2.1
Name: datasci-agents
Version: 0.1.0
Summary: Datasci Agents
Author: Ivan Bestvina
Author-email: ivan.bestvina@qluent.com
Requires-Python: >=3.9,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: colorama (>=0.4.6,<0.5.0)
Requires-Dist: ipykernel (>=6.25.1,<7.0.0)
Requires-Dist: ipython (>=8.14.0,<9.0.0)
Requires-Dist: jupyter-client (>=8.3.0,<9.0.0)
Requires-Dist: litellm (>=0.1.398,<0.2.0)
Requires-Dist: nbformat (>=5.9.2,<6.0.0)
Requires-Dist: pandas (>=2.0.3,<3.0.0)
Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
Requires-Dist: tabulate (>=0.9.0,<0.10.0)
Description-Content-Type: text/markdown


<p align="center">
  <img src="media/image.jpg" height="200" alt="Datasci Agents fig"/>
</p>

Data science agents are LLM-powered helpers designed to help with routine tasks around EDA, feature engineering and modelling.

Although they are able to deliver full datasci projects on their own (and even compete on Kaggle fully autonomously), they are primarily designed as assistants relying on careful human steering.

# Installation
TODO

# Kaggle integration
Coming soon!
