ai-data-science-team
An AI-powered data science team of agents to help you perform common data science tasks 10X faster.
What is ai-data-science-team?
An AI-powered data science team of agents to help you perform common data science tasks 10X faster.
Overview of ai-data-science-team
What it is
AI Data Science Team is a Python library that provides specialized agents for common data science workflows. It includes a flagship application called AI Pipeline Studio, which turns work into a visual, reproducible pipeline. The project is in beta status and breaking changes may occur until version 0.1.0.
Key features
- Pipeline-first workspace with Visual Editor, Table, Chart, EDA, Code, Model, Predictions, and MLflow
- Manual and AI steps with lineage and reproducible scripts
- Multi-dataset handling and merge workflows
- Project saves: metadata-only or full-data
- Storage footprint controls and rehydrate workflows
- Library provides agent building blocks and multi-agent workflows for data loading, cleaning, visualization, modeling, and SQL interaction
Use cases
- Performing data loading and inspection
- Cleaning, wrangling, and feature engineering
- Visualization and exploratory data analysis (EDA)
- Modeling and evaluation using H2O and MLflow tools
- SQL database interaction
- Building multi-agent workflows such as Pandas Data Analyst or SQL Data Analyst
Getting started
Requirements: Python 3.10+ and an OpenAI API key (or Ollama for local models).Clone the repository and install in editable mode:bashpip install -e .Run the AI Pipeline Studio app:bashstreamlit run apps/ai-pipeline-studio-app/app.py
License and pricing
The license is MIT. The project is open source.
Based on the project's public README and repository metadata.