Metadata-Version: 2.1
Name: data-pilot
Version: 0.0.1
Summary: Use LLMs to automate data science tasks
License: MIT
Author: Amar
Author-email: amar439412@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: openai (>=0.27.8,<0.28.0)
Requires-Dist: pandas (>=2.0.3,<3.0.0)
Requires-Dist: pip (>=23.1.2,<24.0.0)
Requires-Dist: pyspark (>=3.4.1,<4.0.0)
Requires-Dist: python-decouple (>=3.8,<4.0)
Requires-Dist: replicate (>=0.8.4,<0.9.0)
Requires-Dist: requests (>=2.31.0,<3.0.0)
Requires-Dist: supabase (>=1.0.3,<2.0.0)
Description-Content-Type: text/markdown

# Data Pilot

*DISCLAIMER: This is a work in progress and currently under development*.

Data Pilot is a python package that automates the process of using Language Models (e.g. GPT-3.5, GPT-4, StableLM, Vicuna40B) to perform Data Science tasks such as data-cleaning, data-preprocessing, data-analysis, and ML model training.

We recommend using OpenAI's models to perform these tasks as they will provide the best output. However, the user is free to choose between a range of different models.

To use data-pilot, you will need two APIs:

- An API for data source : e.g. Supabase, Databricks, or any other Database
- An API for language models : e.g. OpenAI , Replicate

