AI-Powered Research Discovery Platform
CiteMind is a modern AI-powered research discovery platform that revolutionizes how researchers explore, analyze, and connect scientific papers. Built with cutting-edge technologies, it provides intelligent search capabilities, citation network visualization, trend analysis, and AI-powered research synthesis.
- 🔍 AI-Powered Search: Semantic search with natural language processing
- 🕸️ Citation Network Visualization: Interactive network graphs showing paper relationships
- 📈 Research Trends Analysis: Dynamic charts revealing emerging research patterns
- 🏆 Seminal Papers Discovery: Curated lists of influential research papers
- 🤖 AI Research Synthesis: Automated analysis and insights generation
- 🎨 Modern UI/UX: Glassmorphism design with smooth animations
- Next.js 15.4.6 - React framework with App Router
- TypeScript 5.0 - Type-safe development
- Tailwind CSS 4.0 - Modern utility-first CSS framework
- Chart.js 4.5.0 - Interactive data visualization
- D3.js 7.9.0 - Advanced data-driven visualizations
- MongoDB 6.18.0 - NoSQL database for paper storage
- Pinecone - Vector database for semantic search
- HuggingFace Inference - AI model integration
- Node.js APIs - RESTful backend services
- Force-Graph - Network visualization engine
- Vis.js - Advanced network and timeline visualization
- Custom SVG - Citation network rendering
citemind/
├── src/
│ ├── app/ # Next.js App Router pages
│ │ ├── api/ # API routes
│ │ │ ├── query/ # Search and AI analysis
│ │ │ ├── papers/ # Paper management
│ │ │ ├── trends/ # Trend analysis
│ │ │ └── seminal-papers/ # Top papers endpoint
│ │ ├── citation/ # Citation network page
│ │ ├── trends/ # Research trends page
│ │ ├── seminal-papers/ # Top papers page
│ │ ├── loading.tsx # Global loading component
│ │ ├── layout.tsx # Root layout
│ │ └── page.tsx # Homepage
│ └── components/ # Reusable UI components
│ ├── Navbar.tsx # Navigation component
│ ├── PaperItems.tsx # Paper display cards
│ ├── LoadingScreen.tsx # Custom loading screen
│ └── ClientWrapper.tsx # Client-side wrapper
├── public/ # Static assets
└── configuration files
- Node.js (v18 or higher)
- npm or yarn
- MongoDB database
- Pinecone account (for vector search)
- HuggingFace API access
-
Clone the repository
git clone https://github.com/NishantRaj278/CiteMind.git cd CiteMind -
Install dependencies
npm install # or yarn install -
Environment Configuration
Create a
.env.localfile in the root directory:# MongoDB Configuration MONGODB_URI=your_mongodb_connection_string # Pinecone Configuration PINECONE_API_KEY=your_pinecone_api_key PINECONE_INDEX_NAME=your_index_name # HuggingFace Configuration HUGGINGFACE_API_KEY=your_huggingface_api_key
-
Run the development server
npm run dev # or yarn dev -
Open your browser
Navigate to http://localhost:3000
| Endpoint | Method | Description |
|---|---|---|
/api/query |
POST | Search papers and get AI analysis |
/api/papers |
GET | Retrieve all papers |
/api/load-papers |
POST | Load sample papers into database |
/api/trends |
GET | Get research trend analysis |
/api/seminal-papers |
GET | Get top influential papers |
/api/citation-network |
GET | Get citation relationships |
Search with AI Analysis:
const response = await fetch("/api/query", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
query: "machine learning in healthcare",
includeAnalysis: true,
}),
});CiteMind features a modern Glassmorphism design system with:
- Color Palette: Blue to purple gradients (#2563eb → #7c3aed)
- Typography: Montserrat font family with multiple weights
- Components: Backdrop blur effects, gradient backgrounds, smooth animations
- Responsive: Mobile-first design approach
- Accessibility: WCAG 2.1 AA compliant
- MongoDB: Create a database for storing research papers
- Pinecone: Set up a vector index for semantic search
- Collections: The app will automatically create necessary collections
The platform uses HuggingFace models for:
- Text Embedding: Semantic search capabilities
- Text Summarization: Research synthesis
- Analysis Generation: Automated insights
- Semantic similarity search using vector embeddings
- Natural language query processing
- Real-time result filtering and ranking
- AI-generated research synthesis
- Interactive force-directed graph visualization
- Node clustering and relationship mapping
- Hover interactions and detailed paper information
- Export capabilities for further analysis
- Temporal analysis of research patterns
- Dynamic chart generation with Chart.js
- Publication trends over time
- Topic emergence tracking
- Citation-based ranking algorithm
- Curated lists of influential research
- Author impact analysis
- Cross-disciplinary connections
We welcome contributions! Please follow these steps:
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'Add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
- Follow TypeScript best practices
- Use ESLint and Prettier for code formatting
- Write meaningful commit messages
- Add tests for new features
- Update documentation as needed
This project is licensed under the MIT License - see the LICENSE file for details.
Nishant Raj
- GitHub: @NishantRaj278
- LinkedIn: Connect with me
- HuggingFace for AI model APIs
- Pinecone for vector database services
- MongoDB for data storage solutions
- Next.js team for the amazing framework
- Tailwind CSS for the utility-first approach
If you encounter any issues or have questions:
- Check the Issues page
- Create a new issue with detailed description
- Join our community discussions
Built with ❤️ for the research community
⭐ Star this repository if you find it helpful!