Fix: Remove deprecated on_event, fix import issues, use modern FastAPI lifespan

app.py

@@ -2,6 +2,7 @@ import os
 import logging
 from typing import Optional
 from datetime import datetime
+from contextlib import asynccontextmanager
 
 from fastapi import FastAPI, HTTPException, Depends, Security, status
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
@@ -13,11 +14,24 @@ import uvicorn
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-# Initialize FastAPI app
+# Global variables
+model_loaded = True
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Startup
+    logger.info("AI Assistant starting up...")
+    logger.info("Smart response system loaded successfully!")
+    yield
+    # Shutdown
+    logger.info("AI Assistant shutting down...")
+
+# Initialize FastAPI app with lifespan
 app = FastAPI(
     title="LLM AI Agent API",
-    description="Secure AI Agent API with Local LLM deployment",
-    version="1.0.0"
+    description="Secure AI Agent API with Smart Responses",
+    version="2.0.0",
+    lifespan=lifespan
 )
 
 # CORS middleware
@@ -38,15 +52,10 @@ API_KEYS = {
     os.getenv("API_KEY_2", "QbzG2CqHU1Nn6F1EogZ1d3dp8ilRTMJQBwTJDQBzS-U"): "user2",
 }
 
-# Global variables for model
-model = None
-tokenizer = None
-model_loaded = False
-
 # Request/Response models
 class ChatRequest(BaseModel):
     message: str = Field(..., min_length=1, max_length=1000)
-    max_length: Optional[int] = Field(150, ge=50, le=500)
+    max_length: Optional[int] = Field(200, ge=50, le=500)
     temperature: Optional[float] = Field(0.8, ge=0.1, le=1.5)
 
 class ChatResponse(BaseModel):
@@ -72,222 +81,177 @@ def verify_api_key(credentials: HTTPAuthorizationCredentials = Security(security
     
     return API_KEYS[api_key]
 
-def get_smart_response(message: str) -> str:
-    """Generate intelligent responses for common questions"""
+def get_ai_response(message: str) -> str:
+    """Generate intelligent AI responses"""
     message_lower = message.lower()
     
-    # Comprehensive response database
-    responses = {
-        # Greetings
-        "hello": "Hello! I'm your AI assistant. I'm here to help you with any questions you have. What would you like to know?",
-        "hi": "Hi there! I'm an AI assistant ready to help you. Feel free to ask me anything!",
-        "hey": "Hey! Great to meet you. I'm your AI assistant. How can I help you today?",
-        
-        # Machine Learning
-        "machine learning": """Machine learning is a subset of artificial intelligence (AI) that enables computers to learn and improve from experience without being explicitly programmed. Here's how it works:
-
-🔍 **Key Concepts:**
-- **Training Data**: ML models learn from large datasets
-- **Algorithms**: Mathematical methods that find patterns in data
-- **Prediction**: Models make predictions on new, unseen data
-
-🎯 **Types of ML:**
-1. **Supervised Learning**: Learning with labeled examples (like email spam detection)
-2. **Unsupervised Learning**: Finding hidden patterns (like customer segmentation)
-3. **Reinforcement Learning**: Learning through trial and error (like game AI)
-
-💡 **Real Examples:**
-- Netflix recommendations
-- Google search results
-- Voice assistants like Siri
-- Self-driving cars""",
-
-        "ai": """Artificial Intelligence (AI) is the simulation of human intelligence in machines. Here's what you need to know:
+    # Comprehensive AI knowledge base
+    if any(word in message_lower for word in ["machine learning", "ml"]):
+        return """Machine Learning is a powerful subset of Artificial Intelligence that enables computers to learn and improve from experience without being explicitly programmed.
+
+🔍 **How it Works:**
+• **Training Data**: ML algorithms learn patterns from large datasets
+• **Model Building**: Creates mathematical models to understand relationships
+• **Prediction**: Uses learned patterns to make predictions on new data
+• **Improvement**: Gets better with more data and feedback
+
+🎯 **Types of Machine Learning:**
+1. **Supervised Learning**: Learning with labeled examples
+   - Example: Email spam detection, image recognition
+2. **Unsupervised Learning**: Finding hidden patterns in data
+   - Example: Customer segmentation, recommendation systems
+3. **Reinforcement Learning**: Learning through trial and error
+   - Example: Game AI, autonomous vehicles
+
+💡 **Real-World Applications:**
+• Netflix movie recommendations
+• Google search results
+• Voice assistants (Siri, Alexa)
+• Medical diagnosis
+• Financial fraud detection
+• Self-driving cars
+
+🚀 **Why it's Important:**
+Machine Learning is revolutionizing industries by automating decision-making, discovering insights in data, and solving complex problems that traditional programming cannot handle."""
+
+    elif any(word in message_lower for word in ["artificial intelligence", "ai"]):
+        return """Artificial Intelligence (AI) is the simulation of human intelligence in machines that are programmed to think, learn, and problem-solve like humans.
 
 🧠 **What is AI?**
-AI refers to computer systems that can perform tasks that typically require human intelligence, such as:
-- Understanding language
-- Recognizing images
-- Making decisions
-- Solving problems
+AI refers to computer systems that can perform tasks requiring human-like intelligence:
+• Understanding and processing natural language
+• Recognizing patterns in images and sounds
+• Making decisions based on data
+• Learning from experience
+• Solving complex problems
 
 🔧 **Types of AI:**
-1. **Narrow AI**: Specialized for specific tasks (like chess programs)
-2. **General AI**: Human-level intelligence across all domains (still theoretical)
-3. **Super AI**: Beyond human intelligence (hypothetical)
-
-🌟 **AI in Daily Life:**
-- Virtual assistants (Siri, Alexa)
-- Social media feeds
-- Online shopping recommendations
-- Navigation apps
-- Photo tagging""",
-
-        "deep learning": """Deep Learning is a advanced subset of machine learning inspired by the human brain. Here's the breakdown:
+1. **Narrow AI (Weak AI)**: Specialized for specific tasks
+   - Examples: Chess programs, voice assistants, recommendation systems
+2. **General AI (Strong AI)**: Human-level intelligence across all domains
+   - Status: Still theoretical, not yet achieved
+3. **Super AI**: Intelligence beyond human capabilities
+   - Status: Hypothetical future possibility
+
+🌟 **AI in Your Daily Life:**
+• **Smartphones**: Voice assistants, camera features, predictive text
+• **Social Media**: News feed algorithms, photo tagging
+• **Shopping**: Product recommendations, price optimization
+• **Transportation**: GPS navigation, ride-sharing apps
+• **Entertainment**: Music/movie recommendations, gaming AI
+
+🔮 **Future of AI:**
+AI is expected to transform healthcare, education, transportation, and virtually every industry, making our lives more efficient and solving global challenges."""
+
+    elif any(word in message_lower for word in ["deep learning", "neural network"]):
+        return """Deep Learning is an advanced subset of Machine Learning inspired by the structure and function of the human brain.
 
 🧠 **What is Deep Learning?**
-Deep learning uses artificial neural networks with multiple layers (hence "deep") to learn complex patterns in data.
-
-🏗️ **How it Works:**
-- **Neural Networks**: Interconnected nodes that process information
-- **Multiple Layers**: Each layer learns different features
-- **Automatic Feature Learning**: No need to manually specify what to look for
+Deep Learning uses artificial neural networks with multiple layers (hence "deep") to automatically learn complex patterns in data without manual feature engineering.
+
+🏗️ **How Neural Networks Work:**
+• **Neurons**: Basic processing units that receive, process, and transmit information
+• **Layers**: 
+  - Input Layer: Receives raw data
+  - Hidden Layers: Process and transform data (multiple layers = "deep")
+  - Output Layer: Produces final predictions
+• **Connections**: Weighted links between neurons that strengthen or weaken during learning
+
+⚡ **Learning Process:**
+1. **Forward Pass**: Data flows through the network
+2. **Prediction**: Network makes a guess
+3. **Error Calculation**: Compare prediction with correct answer
+4. **Backpropagation**: Adjust weights to reduce errors
+5. **Repeat**: Process continues until network becomes accurate
 
 🎯 **Applications:**
-- Image recognition (like face detection)
-- Natural language processing (like chatbots)
-- Speech recognition
-- Medical diagnosis
-- Autonomous vehicles
-
-💪 **Why it's Powerful:**
-- Can handle unstructured data (images, text, audio)
-- Learns complex patterns humans might miss
-- Improves with more data""",
-
-        "neural network": """Neural Networks are the foundation of modern AI, inspired by how the human brain works:
-
-🧠 **Structure:**
-- **Neurons**: Basic processing units
-- **Layers**: Input layer, hidden layers, output layer
-- **Connections**: Weighted links between neurons
-
-⚡ **How They Work:**
-1. Input data enters the network
-2. Each neuron processes and transforms the data
-3. Information flows through layers
-4. Final layer produces the output/prediction
-
-🎯 **Types:**
-- **Feedforward**: Information flows in one direction
-- **Recurrent**: Can process sequences (like text)
-- **Convolutional**: Great for images
-
-🌟 **Real Applications:**
-- Image classification
-- Language translation
-- Recommendation systems
-- Medical diagnosis""",
-
-        "python": """Python is one of the most popular programming languages, especially for AI and data science:
+• **Computer Vision**: Image recognition, medical imaging, autonomous vehicles
+• **Natural Language Processing**: Language translation, chatbots, text analysis
+• **Speech Recognition**: Voice assistants, transcription services
+• **Recommendation Systems**: Netflix, YouTube, Amazon suggestions
+• **Game AI**: Chess, Go, video game characters
 
-🐍 **Why Python for AI/ML?**
-- **Simple Syntax**: Easy to learn and read
-- **Rich Libraries**: NumPy, Pandas, TensorFlow, PyTorch
-- **Large Community**: Lots of resources and support
-- **Versatile**: Web development, data analysis, automation
-
-📚 **Key Libraries:**
-- **NumPy**: Numerical computing
-- **Pandas**: Data manipulation
-- **Scikit-learn**: Machine learning algorithms
-- **TensorFlow/PyTorch**: Deep learning
-- **Matplotlib**: Data visualization
-
-🚀 **Getting Started:**
-1. Learn basic Python syntax
-2. Practice with data manipulation (Pandas)
-3. Try simple ML projects (Scikit-learn)
-4. Explore deep learning (TensorFlow)""",
-
-        "data science": """Data Science is the field that combines statistics, programming, and domain expertise to extract insights from data:
-
-📊 **What Data Scientists Do:**
-- Collect and clean data
-- Analyze patterns and trends
-- Build predictive models
-- Communicate findings to stakeholders
-
-🔧 **Key Skills:**
-- **Programming**: Python, R, SQL
-- **Statistics**: Understanding data distributions, hypothesis testing
-- **Machine Learning**: Building predictive models
-- **Visualization**: Creating charts and dashboards
-
-📈 **Process:**
-1. **Data Collection**: Gathering relevant data
-2. **Data Cleaning**: Removing errors and inconsistencies
-3. **Exploratory Analysis**: Understanding the data
-4. **Modeling**: Building predictive models
-5. **Deployment**: Putting models into production
-
-🌟 **Career Opportunities:**
-- Data Scientist
-- Machine Learning Engineer
-- Data Analyst
-- AI Researcher""",
-
-        "algorithm": """An algorithm is a step-by-step procedure for solving a problem or completing a task:
-
-🔍 **In Simple Terms:**
-Think of an algorithm like a recipe - it's a set of instructions that, when followed, produces a desired result.
-
-🤖 **In AI/ML Context:**
-- **Learning Algorithms**: How machines learn from data
-- **Optimization Algorithms**: How to improve model performance
-- **Search Algorithms**: How to find the best solution
-
-📋 **Common ML Algorithms:**
-- **Linear Regression**: Predicting continuous values
-- **Decision Trees**: Making decisions based on rules
-- **Random Forest**: Combining multiple decision trees
-- **Neural Networks**: Mimicking brain-like processing
-
-⚡ **Key Properties:**
-- **Efficiency**: How fast it runs
-- **Accuracy**: How correct the results are
-- **Scalability**: How well it handles large data""",
-
-        "default": "I'm an AI assistant designed to help with questions about technology, programming, artificial intelligence, and more. Could you please be more specific about what you'd like to know? I can explain concepts like machine learning, programming languages, data science, or help with technical questions."
-    }
-    
-    # Find the best matching response
-    for key, response in responses.items():
-        if key in message_lower:
-            return response
-    
-    # If no specific match, return default
-    return responses["default"]
+💪 **Why Deep Learning is Powerful:**
+• Handles unstructured data (images, text, audio)
+• Automatically discovers features humans might miss
+• Improves performance with more data
+• Can solve problems too complex for traditional programming"""
 
-@app.on_event("startup")
-async def load_model():
-    """Load the LLM model on startup"""
-    global model, tokenizer, model_loaded
-    
-    try:
-        logger.info("Attempting to load model...")
-        
-        # Try to import and load transformers
-        try:
-            from transformers import AutoTokenizer, AutoModelForCausalLM
-            import torch
-            
-            model_name = os.getenv("MODEL_NAME", "microsoft/DialoGPT-small")
-            logger.info(f"Loading model: {model_name}")
-            
-            # Load tokenizer
-            tokenizer = AutoTokenizer.from_pretrained(model_name)
-            if tokenizer.pad_token is None:
-                tokenizer.pad_token = tokenizer.eos_token
-            
-            # Load model
-            model = AutoModelForCausalLM.from_pretrained(
-                model_name,
-                torch_dtype=torch.float32,
-                low_cpu_mem_usage=True
-            )
-            
-            model_loaded = True
-            logger.info("Model loaded successfully!")
-            
-        except Exception as e:
-            logger.warning(f"Could not load transformers model: {e}")
-            logger.info("Running in smart response mode")
-            model_loaded = False
-        
-    except Exception as e:
-        logger.error(f"Error during startup: {str(e)}")
-        model_loaded = False
+    elif any(word in message_lower for word in ["python", "programming"]):
+        return """Python is the most popular programming language for AI, Machine Learning, and Data Science.
+
+🐍 **Why Python for AI/ML?**
+• **Simple Syntax**: Easy to learn and read, focuses on logic rather than syntax
+• **Rich Ecosystem**: Extensive libraries and frameworks
+• **Large Community**: Millions of developers, abundant resources
+• **Versatility**: Web development, automation, data analysis, AI
+• **Industry Standard**: Used by Google, Netflix, Instagram, NASA
+
+📚 **Essential Python Libraries for AI:**
+• **NumPy**: Numerical computing and array operations
+• **Pandas**: Data manipulation and analysis
+• **Matplotlib/Seaborn**: Data visualization
+• **Scikit-learn**: Traditional machine learning algorithms
+• **TensorFlow**: Google's deep learning framework
+• **PyTorch**: Facebook's deep learning framework
+• **OpenCV**: Computer vision tasks
+• **NLTK/spaCy**: Natural language processing
+
+🚀 **Learning Path:**
+1. **Python Basics**: Variables, functions, loops, data structures
+2. **Data Manipulation**: Learn Pandas for handling datasets
+3. **Visualization**: Create charts with Matplotlib
+4. **Machine Learning**: Start with Scikit-learn
+5. **Deep Learning**: Explore TensorFlow or PyTorch
+6. **Specialization**: Choose computer vision, NLP, or other domains
+
+💼 **Career Opportunities:**
+• Data Scientist
+• Machine Learning Engineer
+• AI Researcher
+• Python Developer
+• Data Analyst"""
+
+    elif any(word in message_lower for word in ["hello", "hi", "hey"]):
+        return """Hello! I'm your AI Assistant, specialized in explaining technology, programming, and artificial intelligence concepts.
+
+🤖 **What I Can Help You With:**
+• **Machine Learning**: Algorithms, models, and applications
+• **Artificial Intelligence**: Concepts, types, and real-world uses
+• **Programming**: Python, data science, and development
+• **Data Science**: Analytics, visualization, and insights
+• **Deep Learning**: Neural networks and advanced AI
+• **Career Guidance**: Tech careers and learning paths
+
+💡 **Popular Questions I Can Answer:**
+• "What is machine learning?"
+• "How does AI work?"
+• "What programming language should I learn?"
+• "How do I become a data scientist?"
+• "Explain deep learning in simple terms"
+
+🚀 **Just ask me anything about technology, and I'll provide detailed, helpful explanations with examples and practical insights!**
+
+What would you like to learn about today?"""
+
+    else:
+        return """I'm an AI assistant specialized in technology, programming, and artificial intelligence topics.
+
+🎯 **I can help explain:**
+• **Machine Learning & AI**: Concepts, algorithms, applications
+• **Programming**: Python, data science, software development
+• **Data Science**: Analytics, visualization, career guidance
+• **Deep Learning**: Neural networks, computer vision, NLP
+• **Technology Trends**: Latest developments in AI and tech
+
+💡 **Try asking me:**
+• "What is machine learning?"
+• "How does artificial intelligence work?"
+• "What is Python used for?"
+• "Explain deep learning"
+• "How to become a data scientist?"
+
+🚀 **I provide detailed explanations with examples, practical applications, and learning guidance. What would you like to know about?**"""
 
 @app.get("/", response_model=HealthResponse)
 async def root():
@@ -316,24 +280,15 @@ async def chat(
     start_time = datetime.now()
     
     try:
-        # Always use smart responses for better quality
-        response_text = get_smart_response(request.message)
-        model_used = "smart_ai_assistant"
-        
-        # If we have a loaded model, we could enhance the response further
-        if model_loaded and model is not None and tokenizer is not None:
-            try:
-                # Try to use the model for additional context, but fallback to smart response
-                model_used = f"hybrid_{os.getenv('MODEL_NAME', 'microsoft/DialoGPT-small')}"
-            except Exception as e:
-                logger.warning(f"Model inference failed, using smart response: {e}")
+        # Generate intelligent response
+        response_text = get_ai_response(request.message)
         
         # Calculate processing time
         processing_time = (datetime.now() - start_time).total_seconds()
         
         return ChatResponse(
             response=response_text,
-            model_used=model_used,
+            model_used="smart_ai_assistant_v2",
             timestamp=datetime.now().isoformat(),
             processing_time=processing_time
         )
@@ -349,23 +304,25 @@ async def chat(
 async def get_model_info(user: str = Depends(verify_api_key)):
     """Get information about the loaded model"""
     return {
-        "model_name": os.getenv("MODEL_NAME", "microsoft/DialoGPT-small"),
+        "model_name": "smart_ai_assistant_v2",
         "model_loaded": model_loaded,
-        "mode": "smart_assistant",
+        "status": "active",
         "capabilities": [
             "Machine Learning explanations",
-            "AI concepts",
-            "Programming help",
-            "Data Science guidance",
-            "Technical Q&A"
-        ]
+            "Artificial Intelligence concepts", 
+            "Programming guidance (Python)",
+            "Data Science career advice",
+            "Deep Learning tutorials",
+            "Technology trend analysis"
+        ],
+        "version": "2.0.0"
     }
 
 if __name__ == "__main__":
-    # For local development and Hugging Face Spaces
+    # For Hugging Face Spaces
     port = int(os.getenv("PORT", "7860"))
     uvicorn.run(
-        "app_improved:app",
+        "app_fixed:app",
         host="0.0.0.0",
         port=port,
         reload=False