Akira is an innovative web application that transforms your markdown notes into interactive mind maps. By leveraging natural language processing and graph visualization using TF-IDF scores and Jaccard-Similarity, Akira helps you understand and connect ideas across multiple documents.
- 🔄 Drag-and-drop file upload
- 📝 Markdown file processing
- 🗺️ Interactive mind map visualization
- 🔍 Zoomable and pannable graphs
- 🔗 Automatic topic connection detection
- React + Vite
- TailwindCSS for styling
- Mermaid.js for mind map visualization
- Lucide React for icons
- Flask (Python)
- NLTK for natural language processing
- scikit-learn for topic extraction
- Beautiful Soup for text processing
- Clone the repository:
git clone https://github.com/yourusername/akira.git
cd akira- Initialise development environment:
devenv up- Install frontend dependencies:
cd akira-frontend
npm install- Download required NLTK data:
python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('wordnet'); nltk.download('averaged_perceptron_tagger')"- In the root directory
devenv up- Navigate to the upload page
- Drag and drop your markdown files or click to select them
- Click "Process Files" to generate the mind map
- Use the zoom controls and drag to explore the generated mind map
- View extracted topics and connections below the visualization
- Supports markdown (.md) files
- Multiple file upload
- Progress indication
- Error handling
- Interactive graph with zoom and pan controls
- Topic clustering by file
- Automatic connection detection between related topics
- Dark theme optimized for readability
- AI-powered topic identification
- Relevance scoring
- Cross-document topic linking
- Natural language processing
- Fork the repository
- Create a feature branch:
git checkout -b feature/YourFeature - Commit your changes:
git commit -m 'Add YourFeature' - Push to the branch:
git push origin feature/YourFeature - Open a pull request
This project is licensed under the GPL3 License - see the LICENSE file for details.
- Built with React and Flask
- Uses NLTK for natural language processing
- Visualization powered by Mermaid.js
- Styled with TailwindCSS