This project provides an experimental web UI for text-to-knowledge-graph generation, targeting developers and researchers interested in interactive data visualization. It offers a novel approach to visualizing knowledge graphs by dynamically updating the graph in real-time as text is input, with color-coded nodes and edges for clarity.

How It Works

The application leverages Flask for its backend and Cytoscape.js for frontend visualization. It uses LiteLLM to process text inputs, transforming them into JSON-formatted graph data. A key design choice is the real-time regeneration of the graph upon detecting a period in the text, enabling an interactive and immediate feedback loop for users.

Quick Start & Requirements

• Install dependencies: poetry install
• Run application: poetry run python main.py
• Requires OPENAI_API_KEY environment variable.
• Access via http://localhost/ in a web browser.

Highlighted Details

• Real-time graph updates on period insertion.
• Color-coded nodes and edges for enhanced visualization.
• Demonstrates a new UI pattern for knowledge graph generation.

Maintenance & Community

This is an experimental project and not intended as a robust framework. Contributions are welcome via pull requests.

Licensing & Compatibility

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

Limitations & Caveats

The project is experimental and may not handle all edge cases or inputs effectively. Future improvements are planned for more sophisticated relationship mapping and incremental graph building.