Create app.py

app.py

@@ -0,0 +1,288 @@
+import google.generativeai as genai
+from dotenv import load_dotenv
+import logging
+import os
+import requests
+from bs4 import BeautifulSoup
+import time
+from datetime import datetime
+import gradio as gr
+
+# ==========================================
+# 1. SETUP & CONFIGURATION
+# ==========================================
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+# Load API Key
+load_dotenv()
+api_key = os.getenv("GEMINI_API_KEY")
+if not api_key:
+    raise ValueError("GEMINI_API_KEY is missing. Check your .env file.")
+
+genai.configure(api_key=api_key)
+
+# ==========================================
+# 2. INTELLIGENT WEB SCRAPER
+# ==========================================
+def fetch_nielit_live_data():
+    """
+    Scrapes official NIELIT websites to create a real-time knowledge base.
+    Implements error handling and rate limiting.
+    """
+    target_urls = [
+        "https://nielit.ac.in/",
+        "https://www.nielit.gov.in/chandigarh/index.php"
+    ]
+    
+    knowledge_base = f"### OFFICIAL LIVE DATA FROM NIELIT (Last Updated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}) ###\n"
+    
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+    }
+    
+    print("⚡ INTELLIGENCE SYSTEM: Scanning NIELIT websites for live data...")
+    
+    for url in target_urls:
+        try:
+            print(f"   📡 Reading: {url}...")
+            response = requests.get(url, headers=headers, timeout=15)
+            
+            if response.status_code == 200:
+                soup = BeautifulSoup(response.content, 'html.parser')
+                
+                # Remove unwanted elements
+                for garbage in soup(["script", "style", "nav", "footer", "aside", "header"]):
+                    garbage.extract()
+                
+                # Extract text and clean whitespace
+                text = soup.get_text(separator=' ', strip=True)
+                
+                # Clean up excessive whitespace
+                text = ' '.join(text.split())
+                
+                # Limit to 8000 chars per site to fit context window efficiently
+                knowledge_base += f"\n--- SOURCE: {url} ---\n{text[:8000]}\n"
+                print(f"   ✅ Successfully scraped {len(text[:8000])} characters")
+            else:
+                logger.warning(f"   ❌ Failed to access {url}: Status {response.status_code}")
+                
+        except requests.exceptions.Timeout:
+            logger.error(f"   ⏱️  Timeout accessing {url}")
+        except requests.exceptions.RequestException as e:
+            logger.error(f"   ❌ Connection error with {url}: {e}")
+        except Exception as e:
+            logger.error(f"   ⚠️  Unexpected error with {url}: {e}")
+        
+        # Rate limiting to be respectful
+        time.sleep(1)
+    
+    return knowledge_base
+
+# ==========================================
+# 3. MODEL SELECTION (Auto-Upgrade)
+# ==========================================
+def get_best_available_model():
+    """
+    Automatically selects the best Gemini model available.
+    """
+    try:
+        available_models = [
+            m.name for m in genai.list_models() 
+            if 'generateContent' in m.supported_generation_methods
+        ]
+        
+        # Priority: Latest Flash -> Pro -> Legacy
+        priority_list = [
+            "models/gemini-1.5-flash-latest",
+            "models/gemini-1.5-flash",
+            "models/gemini-1.5-pro-latest",
+            "models/gemini-1.5-pro",
+            "models/gemini-pro"
+        ]
+        
+        for model in priority_list:
+            if model in available_models:
+                print(f"🧠 MODEL SELECTED: {model}")
+                return model
+                
+        # Fallback to first available
+        if available_models:
+            print(f"🧠 MODEL SELECTED (fallback): {available_models[0]}")
+            return available_models[0]
+        else:
+            raise Exception("No compatible models found")
+            
+    except Exception as e:
+        logger.error(f"Model selection error: {e}")
+        return "models/gemini-pro"
+
+# ==========================================
+# 4. INITIALIZATION
+# ==========================================
+def initialize_bot():
+    """
+    Initializes the chatbot with scraped data and AI model.
+    """
+    print("\n" + "="*60)
+    print("🚀 INITIALIZING NIELIT CHATBOT...")
+    print("="*60)
+    
+    # A. Build the Brain (Scrape once on startup)
+    nielit_data = fetch_nielit_live_data()
+    
+    # B. Define the Persona
+    system_instruction = f"""You are the **Official AI Assistant for NIELIT Ropar/Chandigarh**.
+
+You are professional, accurate, and helpful. Your responses should be clear and concise.
+
+### YOUR KNOWLEDGE BASE:
+{nielit_data}
+
+### RESPONSE GUIDELINES:
+1. **Primary Source**: Answer based strictly on the Knowledge Base above
+2. **Accuracy**: If specific details (fees, dates, faculty names) aren't in the data, say: 
+   "I couldn't find that specific information on the official website. Please visit nielit.ac.in or contact NIELIT directly for the most current details."
+3. **Helpful**: Provide relevant information and suggest where to find more details
+4. **Concise**: Keep answers focused and well-structured
+5. **Professional**: Maintain a helpful, educational tone
+
+### COMMON TOPICS TO ADDRESS:
+- Courses and programs offered
+- Admission procedures and eligibility
+- Fee structure
+- Important dates and deadlines
+- Contact information
+- Center locations
+"""
+    
+    # C. Launch the Brain
+    model_name = get_best_available_model()
+    model = genai.GenerativeModel(
+        model_name=model_name,
+        system_instruction=system_instruction
+    )
+    
+    print("\n✅ INITIALIZATION COMPLETE")
+    print("="*60 + "\n")
+    
+    return model
+
+# Initialize the model globally
+print("Starting bot initialization...")
+MODEL = initialize_bot()
+
+# ==========================================
+# 5. CHAT FUNCTIONS FOR GRADIO
+# ==========================================
+def chat_response(message, history):
+    """
+    Processes user message and returns bot response.
+    Compatible with Gradio ChatInterface.
+    """
+    try:
+        response = MODEL.generate_content(
+            message,
+            generation_config=genai.types.GenerationConfig(
+                temperature=0.3,
+                max_output_tokens=800,
+            )
+        )
+        return response.text
+    except Exception as e:
+        logger.error(f"Error generating response: {e}")
+        return f"⚠️ I encountered an error processing your question. Please try rephrasing or ask something else."
+
+# ==========================================
+# 6. GRADIO INTERFACE
+# ==========================================
+def create_gradio_interface():
+    """
+    Creates and configures the Gradio chat interface.
+    """
+    
+    # Custom CSS for styling
+    custom_css = """
+    .contain { max-width: 1200px; margin: auto; padding-top: 1.5rem; }
+    .avatar-container img { border-radius: 50%; }
+    footer {visibility: hidden}
+    """
+    
+    # Check if bot.png exists
+    bot_avatar = "bot.png" if os.path.exists("bot.png") else None
+    
+    # Create the chat interface
+    demo = gr.ChatInterface(
+        fn=chat_response,
+        title="🎓 NIELIT Ropar/Chandigarh - Official AI Assistant",
+        description="""
+        Welcome to the **NIELIT Chatbot**! Ask me anything about:
+        - 📚 Courses and Programs
+        - 📝 Admission Procedures
+        - 💰 Fee Structure
+        - 📅 Important Dates
+        - 📞 Contact Information
+        - 📍 Center Locations
+        
+        *Powered by Google Gemini AI with live website data*
+        """,
+        examples=[
+            "What courses are available at NIELIT?",
+            "How do I apply for admission?",
+            "What is the fee structure?",
+            "What are the eligibility criteria?",
+            "Where is NIELIT Chandigarh located?",
+            "Tell me about the institute"
+        ],
+        theme=gr.themes.Soft(
+            primary_hue="blue",
+            secondary_hue="slate",
+        ),
+        css=custom_css,
+        retry_btn="🔄 Retry",
+        undo_btn="↩️ Undo",
+        clear_btn="🗑️ Clear",
+        submit_btn="Send 📤",
+        chatbot=gr.Chatbot(
+            height=500,
+            avatar_images=(None, bot_avatar),
+            bubble_full_width=False,
+            show_copy_button=True,
+        ),
+        textbox=gr.Textbox(
+            placeholder="Type your question here...",
+            container=False,
+            scale=7
+        ),
+    )
+    
+    return demo
+
+# ==========================================
+# 7. MAIN EXECUTION
+# ==========================================
+if __name__ == "__main__":
+    try:
+        print("\n🚀 Launching Gradio Interface...")
+        
+        # Create and launch the interface
+        demo = create_gradio_interface()
+        
+        # Launch with share=True to get a public link (optional)
+        demo.launch(
+            server_name="0.0.0.0",  # Accessible from network
+            server_port=7860,        # Default Gradio port
+            share=False,             # Set to True for public link
+            show_error=True,
+            favicon_path="bot.png" if os.path.exists("bot.png") else None
+        )
+        
+    except KeyboardInterrupt:
+        print("\n\n👋 Program interrupted. Goodbye!")
+    except Exception as e:
+        logger.error(f"Fatal error: {e}")
+        print(f"\n❌ A critical error occurred: {e}")
+        print("Please check your configuration and try again.")