GuardChat 🛡️💬

An intelligent document chat system that enables secure, role-based conversations with organizational documents. Users can query company policies, technical documentation, and confidential files through natural language, with AI-powered responses that respect access permissions and maintain data security.

✨ Key Features

• 🔐 Role-based Access Control - Admin, Manager, Employee, Intern permissions
• 🤖 AI-Powered Q&A - Natural language queries using Groq LLaMA 3.1
• 📄 Multi-format Support - PDF, DOCX, TXT, MD document processing
• 🔍 Semantic Search - FAISS vector store for intelligent document retrieval
• 💬 Real-time Chat - WebSocket-powered conversations with history
• 📊 Admin Dashboard - Document management and audit logging
• 🎨 Modern UI - Glassmorphism design with dark/light themes
• 🔒 Security First - JWT authentication and comprehensive audit trails

🚀 Quick Start

Prerequisites

• Python 3.8+
• Node.js 16+
• Git

1. Clone Repository

git clone https://github.com/sachin9536/guard-chat.git
cd guard-chat

2. Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

3. Environment Configuration

Create .env file in backend directory:

GROQ_API_KEY=your_groq_api_key_here
SECRET_KEY=your_secret_key_here
ENVIRONMENT=development

4. Frontend Setup

cd ../frontend
npm install

5. Run Application

# Terminal 1 - Backend
cd backend
python main.py

# Terminal 2 - Frontend
cd frontend
npm run dev

Visit http://localhost:5173 to access GuardChat!

🏗️ Architecture

GuardChat/
├── backend/                 # FastAPI backend
│   ├── main.py             # API server
│   ├── database.py         # SQLite database
│   ├── vector_store.py     # FAISS vector operations
│   ├── auth.py             # JWT authentication
│   └── indexing.py         # Document processing
├── frontend/               # React frontend
│   ├── src/
│   │   ├── components/     # UI components
│   │   ├── pages/          # Application pages
│   │   └── utils/          # API utilities
├── demo-documents/         # Sample documents
└── docker-compose.yml      # Docker deployment

🔧 Built With

Backend

• FastAPI - High-performance Python web framework
• SQLite - Lightweight database for data persistence
• FAISS - Facebook AI Similarity Search for vector operations
• Groq API - LLaMA 3.1 language model integration
• LangChain - Document processing and chunking
• Sentence Transformers - Text embeddings (all-mpnet-base-v2)
• python-docx - DOCX document processing
• PyPDF2 - PDF document processing
• WebSockets - Real-time communication
• JWT - Secure authentication tokens

Frontend

• React 18 - Modern UI library
• Vite - Fast build tool and dev server
• Tailwind CSS - Utility-first CSS framework
• Lucide React - Beautiful icon library
• Axios - HTTP client for API calls

👥 Default Users

Username	Password	Role	Access Level
admin	admin123	Admin	Full system access
manager	manager123	Manager	Department documents
employee	employee123	Employee	General documents
intern	intern123	Intern	Public documents only

📚 API Documentation

Once running, visit:

• Interactive API Docs: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

Key Endpoints

POST /login              # User authentication
POST /query              # Document Q&A
POST /upload             # Document upload
GET  /documents          # List documents
POST /request-access     # Request document access
GET  /conversations      # Chat history

🐳 Docker Deployment

Development

docker-compose up --build

Production

docker-compose -f docker-compose.yml up -d

Access at http://localhost:80

🔒 Security Features

• JWT Authentication - Secure token-based auth
• Role-based Access Control - Granular permissions
• Audit Logging - Complete activity tracking
• Input Validation - SQL injection prevention
• Rate Limiting - API abuse protection
• CORS Configuration - Cross-origin security

📖 Usage Examples

Document Upload

# Admin uploads a confidential document
POST /upload
{
  "file": "salary_matrix.pdf",
  "roles": ["Admin", "Manager"],
  "categories": ["HR", "Confidential"]
}

Query Documents

# Employee asks about company policy
POST /query
{
  "query": "What is the remote work policy?",
  "user_role": "Employee"
}

Access Request

# Intern requests access to restricted document
POST /request-access
{
  "document_id": "doc-123",
  "message": "Need access for project research"
}

🤝 Contributing

1. Fork the repository
2. Create feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Groq for lightning-fast LLaMA inference
• FAISS for efficient vector similarity search
• LangChain for document processing utilities
• FastAPI for the excellent web framework
• React community for amazing UI components

📞 Support

• 📧 Email: sachinchoudharyxyz9@gmail.com
• 🐛 Issues: GitHub Issues
• 💬 Discussions: GitHub Discussions

---

Built with ❤️ by Sachin Choudhary