demo_groq.py

"""
Demo script for OneHourBook with Groq API integration.
Shows model switching capabilities.
"""
import asyncio
import sys
import os
from pathlib import Path

# Load environment variables
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass  # Silently continue if dotenv not available

# Add src to path
sys.path.append(str(Path(__file__).parent / "src"))

def print_header():
    """Print demo header."""
    print("=" * 80)
    print("🤖 ONEHOURBOOK WITH GROQ API")
    print("   ChronosReader & 14-Agent Swarm")
    print("   Multiple Model Support")
    print("=" * 80)
    print()


def show_available_models():
    """Show available Groq models."""
    print("🔧 AVAILABLE GROQ MODELS:")
    print("-" * 40)
    
    models = [
        ("llama-3.3-70b-versatile", "🦙 Llama 3.3 70B", "Best for complex reasoning & analysis"),
        ("llama-3.1-70b-versatile", "🦙 Llama 3.1 70B", "Great balance of speed & capability"),
        ("llama-3.1-8b-instant", "⚡ Llama 3.1 8B", "Fastest option for simple tasks"),
        ("mixtral-8x7b-32768", "🎭 Mixtral 8x7B", "Excellent for creative writing"),
        ("gemma2-9b-it", "💎 Gemma2 9B", "Efficient for basic processing"),
        ("gemma-7b-it", "💎 Gemma 7B", "Lightweight option")
    ]
    
    for model_id, name, description in models:
        print(f"   {name:20} | {model_id:25} | {description}")
    
    print()


def simulate_model_switching():
    """Simulate switching between models for different tasks."""
    print("🔄 MODEL SWITCHING DEMONSTRATION:")
    print("-" * 40)
    
    tasks = [
        ("📚 Book Intake", "llama-3.3-70b-versatile", "Complex metadata resolution"),
        ("🧠 Context Analysis", "llama-3.1-70b-versatile", "Author background research"),
        ("⚡ Chapter Processing", "llama-3.1-8b-instant", "Fast parallel processing"),
        ("💎 Quote Extraction", "mixtral-8x7b-32768", "Creative quote selection"),
        ("🔍 Fact Checking", "llama-3.3-70b-versatile", "Rigorous validation"),
        ("📄 Export Generation", "gemma2-9b-it", "Template formatting")
    ]
    
    print("Task                  | Model Used              | Reasoning")
    print("-" * 70)
    
    for task, model, reasoning in tasks:
        print(f"{task:20} | {model:23} | {reasoning}")
    
    print()


def show_usage_examples():
    """Show usage examples with different models."""
    print("📋 USAGE EXAMPLES:")
    print("-" * 40)
    
    examples = [
        "# Default (Llama 3.3 70B for best quality)",
        'python src/main.py --book-title "Thinking, Fast and Slow" --author "Daniel Kahneman"',
        "",
        "# Fast processing with Llama 8B",
        'python src/main.py --book-title "Atomic Habits" --author "James Clear" \\',
        '                   --model "llama-3.1-8b-instant"',
        "",
        "# Creative analysis with Mixtral",
        'python src/main.py --book-title "The Great Gatsby" --author "F. Scott Fitzgerald" \\',
        '                   --model "mixtral-8x7b-32768" --public-domain',
        "",
        "# User text with custom model",
        'python src/main.py --book-title "Your Book" --author "Your Author" \\',
        '                   --user-text book.txt --model "llama-3.1-70b-versatile"'
    ]
    
    for example in examples:
        print(example)
    
    print()


def check_environment():
    """Check if Groq API key is configured."""
    print("🔐 ENVIRONMENT CHECK:")
    print("-" * 40)
    
    groq_key = os.getenv("GROQ_API_KEY")
    if groq_key:
        # Mask the key for security
        masked_key = groq_key[:8] + "..." + groq_key[-4:] if len(groq_key) > 12 else "***"
        print(f"✅ GROQ_API_KEY found: {masked_key}")
        print("   Ready for real book processing!")
    else:
        print("❌ GROQ_API_KEY not found")
        print("   Set your API key:")
        print("   export GROQ_API_KEY=your_key_here")
        print("   Or add to .env file")
    
    print()


async def test_groq_connection():
    """Test connection to Groq API."""
    groq_key = os.getenv("GROQ_API_KEY")
    if not groq_key:
        print("⏭️  Skipping connection test (no API key)")
        return
    
    print("🔌 TESTING GROQ CONNECTION:")
    print("-" * 40)
    
    try:
        from frameworks.groq_client import GroqClient
        
        client = GroqClient(model="llama-3.1-8b-instant")
        
        print("⏳ Testing connection with Llama 3.1 8B...")
        
        response = await client.complete(
            prompt="Hello! Please respond with exactly 5 words.",
            max_tokens=20,
            temperature=0.1
        )
        
        content = response["choices"][0]["message"]["content"]
        print(f"✅ Connection successful!")
        print(f"   Response: {content}")
        
        # Test model switching
        print("\n⏳ Testing model switch to Llama 3.3 70B...")
        client.set_model("llama-3.3-70b-versatile")
        
        response2 = await client.complete(
            prompt="What is the capital of France? One word only.",
            max_tokens=10,
            temperature=0.1
        )
        
        content2 = response2["choices"][0]["message"]["content"]
        print(f"✅ Model switching successful!")
        print(f"   Response: {content2}")
        
        await client.close()
        
    except Exception as e:
        print(f"❌ Connection failed: {e}")
        print("   Check your API key and internet connection")
    
    print()


def show_configuration():
    """Show current configuration."""
    print("⚙️  SYSTEM CONFIGURATION:")
    print("-" * 40)
    
    try:
        from utils.io import load_config
        config = load_config("configs/settings.yaml")
        
        llm_config = config.get("llm", {})
        print(f"Provider: {llm_config.get('provider', 'groq')}")
        print(f"Default Model: {llm_config.get('model', 'llama-3.3-70b-versatile')}")
        print(f"Max Tokens: {llm_config.get('max_tokens', 4096)}")
        print(f"Temperature: {llm_config.get('temperature', 0.1)}")
        print(f"Rate Limit: {llm_config.get('rate_limit_requests_per_minute', 30)} req/min")
        
    except Exception as e:
        print(f"Could not load config: {e}")
    
    print()


def main():
    """Run the demo."""
    try:
        print_header()
        
        print("📖 DEMONSTRATION: The Art of War by Sun Tzu")
        print("🔓 STATUS: Public Domain (Ancient text)")
        print("⏱️  TARGET: 230 WPM → 13,800 words (58-60 minutes)")
        print()
        
        show_available_models()
        simulate_model_switching()
        show_configuration()
        check_environment()
        
        # Test connection if API key is available
        print("🧪 RUNNING CONNECTION TEST...")
        print("-" * 40)
        asyncio.run(test_groq_connection())
        
        show_usage_examples()
        
        print("🎯 DEMO COMPLETE!")
        print("-" * 40)
        print("✅ Groq API integration configured")
        print("✅ Multiple model support enabled")
        print("✅ Model switching capabilities demonstrated")
        print("✅ Ready for real book processing!")
        print()
        print("To process a real book:")
        print('python src/main.py --book-title "Your Book" --author "Author Name"')
        
        return 0
        
    except KeyboardInterrupt:
        print("\n⏹️  Demo interrupted by user")
        return 130
    except Exception as e:
        print(f"\n❌ Demo failed: {e}")
        return 1


if __name__ == "__main__":
    exit_code = main()
    sys.exit(exit_code)