Probly is a next-generation spreadsheet application that combines the power of traditional spreadsheets with AI-driven analysis, Python computation, and intelligent document processing.
- Smart Spreadsheet: Full-featured spreadsheet with formula support and intelligent cell suggestions
- Python Integration: Run Python code directly in your browser using WebAssembly
- Data Visualization: Create interactive charts and visualizations
- AI-Powered Analysis: Get intelligent insights and automated trend analysis
- Document Processing: Extract and process data from images.
- Prompt Library: Access predefined analysis templates and save custom prompts
Probly leverages a modern, privacy-focused architecture:
graph LR
A[Browser] --> B[Next.js Frontend]
B --> C[Pyodide/WASM]
B --> D[OpenAI API]
B --> E[Vision API]
C --> F[Local Processing]
D --> G[AI Analysis]
E --> H[Document Processing]
- Frontend: Next.js 14 with TypeScript and React
- Python Runtime: Pyodide (WebAssembly) for local execution
- AI Integration: OpenAI API for intelligent analysis
- Document Processing: Vision API for extracting data from documents
- Interactive Spreadsheet: Full-featured spreadsheet with formula support
- Python Analysis: Run Python code directly in your browser using WebAssembly
- Data Visualization: Create charts and visualizations from your data
- AI-Powered: Get intelligent suggestions and automated analysis
- Prompt Library: Access predefined prompts or save your own for quick reuse
Probly uses a modern architecture:
- Frontend: Next.js application that runs in the browser
- Python Execution: Pyodide (Python compiled to WebAssembly) runs entirely in the browser
- LLM Integration: OpenAI API calls are proxied through the server
This design means that data analysis happens locally in your browser, providing better performance and privacy.
- Node.js 18 or higher
- npm or yarn
- A modern web browser (Chrome, Firefox, Edge, or Safari)
- OpenAI API key
The fastest way to get started with Probly:
-
📥 Clone the repository:
git clone https://github.com/PragmaticMachineLearning/probly.git cd probly -
🔑 Create a
.envfile with your OpenAI API key:OPENAI_API_KEY=your_api_key_here
-
🐳 Build and start with Docker:
docker compose build docker compose up -d
-
🌐 Access Probly at http://localhost:3000
Prefer running without Docker? Here's how:
-
📥 Clone the repository:
git clone https://github.com/PragmaticMachineLearning/probly.git cd probly -
📦 Install dependencies:
npm install
-
🔑 Set up your environment:
OPENAI_API_KEY=your_api_key_here
-
🚀 Start development server:
npm run dev
- 🌐 Launch the application in your browser
- 📤 Import your data or start with a blank sheet
- 🤖 Access AI features with keyboard shortcuts:
- Windows/Linux:
Ctrl+Shift+? - Mac:
⌘+Shift+?
- Windows/Linux:
- 📚 Use the prompt library for quick analysis
- 📄 Upload documents for automatic data extraction
- 💬 Ask questions about your data in natural language
| Action | Windows/Linux | Mac |
|---|---|---|
| AI Chat | Ctrl+Shift+? |
⌘+Shift+? |
| Prompt Library | Ctrl+Shift+L |
⌘+Shift+L |
- Frontend: Next.js 14, TypeScript, React
- Spreadsheet: Handsontable, HyperFormula
- Python: Pyodide (WebAssembly)
- AI: OpenAI API (GPT-4, Vision API)
- Visualization: ECharts
For detailed documentation, visit our Probly Documentation.
Join our Discord community to:
- 💡 Share ideas and get help
- 🎉 Stay updated on new features
- 👥 Connect with other users
- 🤝 Contribute to development
MIT License - Feel free to use and modify!