latest

README.md

@@ -5,9 +5,10 @@ A modern, bilingual (Arabic/English) university portal for the University of Tas
 ## 🌟 Features
 
 ### 🤖 AI-Powered Chatbot
-- **Real AI**: Uses OpenRouter API with Meta LLaMA model
+- **Real AI**: Uses OpenRouter API with Meta LLaMA model or Ollama local models
 - **Bilingual Support**: Automatically detects and responds in Arabic or English
 - **UTAS Oman Context**: Specialized knowledge about campus, programs, and admissions
+- **Personalized Responses**: Tailors answers based on user authentication and role
 - **No Mock Data**: All responses generated by real AI
 
 ### 🎓 Academic Programs
@@ -64,6 +65,56 @@ A modern, bilingual (Arabic/English) university portal for the University of Tas
 5. **Open your browser**
    Navigate to [http://localhost:3000](http://localhost:3000)
 
+## 🤖 Chatbot Setup
+
+### Configuration
+
+1. Create a `.env.local` file in the project root with the following variables:
+
+   ```env
+   # OpenRouter API Key (for LLM access)
+   OPENROUTER_API_KEY=sk-your-key-here
+   
+   # Ollama configuration (for local model fallback)
+   OLLAMA_URL=http://localhost:11434
+   MODEL_COMMAND_R7B=command-r7b-arabic
+   ```
+
+2. To use the Ollama fallback:
+   
+   - Install Ollama from [https://ollama.ai/](https://ollama.ai/)
+   - Pull the Arabic-capable model: `ollama pull command-r7b-arabic`
+   - Start the Ollama server locally: `ollama serve`
+   
+3. The chatbot automatically:
+   - Tries OpenRouter first if API key is available
+   - Falls back to Ollama if OpenRouter key is missing
+   - Detects language (Arabic/English) and responds accordingly
+   - Personalizes responses based on user authentication status
+
+### Testing the Chatbot
+
+Run the built-in chatbot tests:
+
+```bash
+npm run test:chat
+```
+
+Or run the integration tests:
+
+```bash
+npm run test
+```
+
+### Personalization Features
+
+The chatbot provides different responses based on authentication:
+
+- **Anonymous Users**: Public information only (courses, admissions, etc.)
+- **Authenticated Students**: Personalized responses with student profile data
+- **Faculty/Staff**: More detailed institutional information
+- **Administrators**: Full access to university systems information
+
 ## 🛠️ Technology Stack
 
 - **Framework**: Next.js 14+ with React 19