Auto-Analyst is an AI-driven data analytics system designed to simplify complex data science tasks for analysts and scientists. It leverages specialized AI agents within an interactive Streamlit interface for automated data preprocessing, statistical analysis, machine learning, and visualization, aiming to enhance efficiency and accessibility.

How It Works

The system employs a modular agent-based architecture, with specialized agents for visualization (Plotly), statistical analysis, scikit-learn integration, and data preprocessing. It utilizes DSPy for lightweight framework integration and is designed to be LLM-agnostic, allowing flexibility in AI model selection. An overarching "auto_analyst_ind" agent routes queries to the appropriate specialized agent, while "auto_analyst" handles planning and output synthesis.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Set OPENAI_API_KEY environment variable.
• Run the app: streamlit run new_frontend.py
• Requires Python 3.x and an OpenAI API key.

Highlighted Details

• Plug-and-play Streamlit UI for interactive data visualization and analysis.
• Specialized agents for data visualization, statistical analysis, machine learning (scikit-learn), and preprocessing.
• LLM-agnostic design for adaptability to various AI models.
• Built using lightweight frameworks like DSPy.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (Discord/Slack) is provided in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The system explicitly requires an OpenAI API key, limiting its LLM-agnostic claim in practice for core functionality. The README does not detail performance benchmarks or specific limitations of the agents.