An AI-powered marketing chatbot with intelligent product search, persistent chat history, and aggressive sales conversion optimization.

• 🤖 AI-Powered Sales Agent - GPT-3.5 Turbo with aggressive sales prompting
• 🔍 Intelligent Product Search - Multi-strategy search with full-text capabilities
• 💬 Persistent Chat History - Cross-session conversation management
• ⚡ Real-time Streaming - Token-by-token response streaming
• 📱 Responsive Design - Mobile-first UI with modern components
• 🔒 Secure & Validated - Input sanitization and type-safe APIs

• Frontend: Next.js 14+, TypeScript, Tailwind CSS, shadcn/ui
• Backend: Node.js, PostgreSQL, Drizzle ORM
• AI: OpenAI GPT-3.5 Turbo via Vercel AI SDK
• Database: PostgreSQL with GIN indexes for full-text search

• Node.js 18+
• PostgreSQL 13+
• OpenAI API key

1. Clone the repository

   git clone <repository-url>
   cd marketbot-agent

2. Install dependencies

   npm install

3. Set up environment variables

   cp .env.example .env.local

   Configure the following variables:

   DATABASE_URL="postgresql://username:password@localhost:5432/marketbot"
   OPENAI_API_KEY="your-openai-api-key"
   NODE_ENV="development"

4. Set up the database

   # Create database
   createdb marketbot
   
   # Run migrations
   npm run db:migrate
   
   # Seed sample data (optional)
   npm run db:seed

5. Start the development server

   npm run dev

   Open http://localhost:3000 in your browser.

The application uses PostgreSQL with advanced indexing for optimal search performance. Key features:

• GIN indexes for full-text search on product names and descriptions
• JSONB support for flexible product features and tags
• Connection pooling for scalable concurrent access
• Automatic session cleanup for expired conversations

• products - Product catalog with full-text search capabilities
• chat_sessions - User conversation sessions with auto-expiration
• chat_messages - Individual messages with product context linking

• GET /api/products - Search products with filtering and pagination
• GET /api/products/[id] - Get single product details
• POST /api/products - Create new product
• PUT /api/products/[id] - Update product
• DELETE /api/products/[id] - Delete product

• POST /api/chat/stream - Stream AI responses
• GET /api/chat/history - Get conversation history
• DELETE /api/chat/history - Clear conversation history
• POST /api/chat/history/save - Save message

• GET /api/chat/sessions - List user sessions
• DELETE /api/chat/sessions - Delete session
• PUT /api/chat/sessions/rename - Rename session

1. Start a conversation - The AI agent will greet you and ask about your product interests
2. Search for products - Ask about specific products or categories
3. Get recommendations - The AI will suggest relevant products based on your queries
4. View chat history - Access previous conversations from the sidebar
5. Manage sessions - Rename or delete conversation sessions

Connection pooling settings (adjust in db/index.ts):

const pool = new Pool({
  connectionString: process.env.DATABASE_URL,
  max: 10,                    // Maximum connections
  idleTimeoutMillis: 30000,   // Close idle connections
  connectionTimeoutMillis: 2000
});

npm run dev          # Start development server
npm run build        # Build for production
npm run start        # Start production server
npm run lint         # Run ESLint
npm run type-check   # Run TypeScript checks
npm run db:migrate   # Run database migrations
npm run db:seed      # Seed sample data

├── app/                 # Next.js app directory
│   ├── api/            # API routes
│   ├── globals.css     # Global styles
│   ├── layout.tsx      # Root layout
│   └── page.tsx        # Home page
├── components/         # React components
│   ├── chat/          # Chat-related components
│   └── ui/            # UI components (shadcn/ui)
├── db/                # Database configuration
│   ├── index.ts       # Database connection
│   └── schema.ts      # Drizzle schema
├── lib/               # Utility libraries
│   ├── chat-history.ts # Chat history service
│   ├── db-service.ts   # Database service
│   ├── prompt.ts       # AI prompt configuration
│   └── validation.ts   # Input validation schemas
└── public/            # Static assets

1. Set up production PostgreSQL database
2. Configure environment variables
3. Run database migrations
4. Build and deploy the application
5. Set up health monitoring on /api/health

• Database connection pooling is configured for production use
• GIN indexes optimize search performance
• Session cleanup prevents memory leaks
• Response streaming improves perceived performance