LocalChat.ai

A LocalChat.ai application powered by the DeepSeek API, featuring a modern chat interface with customizable response styles and conversation management.

Features

• 🤖 DeepSeek API Integration - High-performance AI chat with cost-effective pricing
• 🎨 Multiple Response Styles - Balanced, Concise, Explanatory, Formal, and Friendly modes
• 💬 Conversation Management - Persistent chat history with local storage
• 🔄 Real-time Streaming - Smooth, responsive chat experience
• 📱 Responsive Design - Works seamlessly on desktop and mobile
• 🛡️ Robust Error Handling - Graceful fallbacks and retry mechanisms
• 💾 Data Export/Import - Backup and restore your conversations
• ⚡ Context Management - Automatic context window optimization

Quick Start

Prerequisites

• Node.js 16+ and npm
• DeepSeek API key (Get yours here)

Installation

1. Clone the repository

   git clone <your-repo-url>
   cd LocalChat.ai

2. Install dependencies

   npm install

3. Set up environment variables

   cp .env.example .env

   Edit .env and add your DeepSeek API key:

   DEEPSEEK_API_KEY=your_api_key_here
   DEEPSEEK_BASE_URL=https://api.deepseek.com
   PORT=3001
   

4. Start the application

   npm start

   This will start both the backend server (port 3001) and frontend (port 3000).

5. Open in browser

   http://localhost:3000
   

Architecture

Backend (/server)

• Express.js server with API routes
• DeepSeek API integration with retry logic
• Prompt templates system for style customization
• Error handling with proper HTTP status codes

Frontend (/src)

• React 18 with modern hooks
• Component-based architecture
• Local storage for conversation persistence
• Axios for API communication
• Markdown rendering for AI responses

Key Components

src/
├── components/
│   ├── ChatSidebar.jsx      # Conversation history
│   ├── ChatHeader.jsx       # Style selector
│   ├── ChatContainer.jsx    # Message display
│   ├── Message.jsx          # Individual message
│   └── MessageInput.jsx     # Input area
├── services/
│   ├── chatService.js       # API communication
│   └── conversationManager.js # Local storage
└── utils/
    └── errorHandling.js     # Error management

Response Styles

The application supports five different response styles:

• Balanced - Well-rounded responses with appropriate detail
• Concise - Brief, direct answers focused on key points
• Explanatory - Detailed explanations with context and examples
• Formal - Professional tone suitable for business contexts
• Friendly - Warm, conversational tone for casual interactions

Configuration

Environment Variables

Variable	Description	Default
DEEPSEEK_API_KEY	Your DeepSeek API key	Required
DEEPSEEK_BASE_URL	DeepSeek API endpoint	https://api.deepseek.com
PORT	Backend server port	3001

DeepSeek API Settings

The application is configured with optimal settings for chat:

• Model: deepseek-chat
• Temperature: 0.7 (balanced creativity)
• Max Tokens: 4000 (substantial responses)
• Top-p: 0.95 (diverse vocabulary)

Storage & Privacy

• Local Storage Only - All conversations stored in browser
• No Cloud Sync - Complete privacy and control
• Export/Import - JSON format for backup
• Automatic Cleanup - Limits storage to prevent bloat

Error Handling

The application includes comprehensive error handling:

• Network Errors - Retry with exponential backoff
• Rate Limiting - Automatic retry with appropriate delays
• API Errors - User-friendly error messages
• Storage Errors - Graceful degradation
• Context Overflow - Automatic message truncation

Development

Project Structure

LocalChat.ai/
├── src/                 # React frontend
│   ├── components/      # UI components
│   ├── services/        # Business logic
│   └── utils/           # Utilities
├── server/              # Express backend
│   ├── routes/          # API endpoints
│   └── services/        # Backend services
├── package.json         # Dependencies
└── vite.config.js       # Build configuration

Available Scripts

npm run dev      # Start frontend development server
npm run server   # Start backend server only
npm start        # Start both frontend and backend
npm run build    # Build for production
npm run preview  # Preview production build

API Endpoints

• POST /api/chat/message - Send chat message
• GET /api/chat/styles - Get available response styles
• GET /api/health - Health check

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

• 📖 Check the DeepSeek API Documentation
• 🐛 Report issues on GitHub
• 💡 Feature requests welcome

---

Built with ❤️ using DeepSeek AI and modern web technologies.