Upload 7 files

config.py

@@ -0,0 +1,55 @@
+"""
+Configuration file for the Inclusive World Curriculum Assistant
+"""
+
+# Model Configuration
+MODEL_CONFIG = {
+    "model_name": "microsoft/DialoGPT-medium",
+    "embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
+    "max_new_tokens": 256,
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "repetition_penalty": 1.15,
+    "torch_dtype": "float16",
+    "device_map": "auto",
+    "trust_remote_code": True
+}
+
+# Vector Database Configuration
+VECTOR_DB_CONFIG = {
+    "chunk_size": 1000,
+    "chunk_overlap": 200,
+    "persist_directory": "./chroma_db",
+    "search_kwargs": {"k": 3}
+}
+
+# File Processing Configuration
+FILE_CONFIG = {
+    "slides_directory": "Slides",
+    "supported_formats": [".pdf"],
+    "max_preview_length": 500
+}
+
+# UI Configuration
+UI_CONFIG = {
+    "page_title": "Inclusive World Curriculum Assistant",
+    "page_icon": "🎓",
+    "layout": "wide",
+    "initial_sidebar_state": "expanded"
+}
+
+# Curriculum Topics (for quick access)
+CURRICULUM_TOPICS = [
+    "Variables and Data Types",
+    "Control Structures (if/else)",
+    "Loops (for, while)",
+    "Functions and Methods",
+    "Arrays and Lists",
+    "Object-Oriented Programming",
+    "Error Handling",
+    "File Operations",
+    "Web Development Basics",
+    "Database Fundamentals",
+    "API Development",
+    "Testing Strategies"
+] 

run.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""
+Launcher script for Inclusive World Curriculum Assistant
+"""
+
+import os
+import sys
+import subprocess
+from pathlib import Path
+
+def check_environment():
+    """Check if the environment is properly set up"""
+    print("🔍 Checking environment...")
+    
+    # Check if required files exist
+    required_files = ["app.py", "config.py", "utils.py", "requirements.txt"]
+    missing_files = []
+    
+    for file in required_files:
+        if not Path(file).exists():
+            missing_files.append(file)
+    
+    if missing_files:
+        print(f"❌ Missing required files: {', '.join(missing_files)}")
+        return False
+    
+    # Check if Slides directory exists
+    if not Path("Slides").exists():
+        print("⚠️  Slides directory not found. Creating...")
+        Path("Slides").mkdir(exist_ok=True)
+    
+    print("✅ Environment check passed")
+    return True
+
+def check_dependencies():
+    """Check if dependencies are installed"""
+    print("📦 Checking dependencies...")
+    
+    try:
+        import streamlit
+        import langchain
+        import chromadb
+        import transformers
+        import torch
+        import fitz
+        print("✅ All dependencies are installed")
+        return True
+    except ImportError as e:
+        print(f"❌ Missing dependency: {e}")
+        print("Please run: pip install -r requirements.txt")
+        return False
+
+def start_application():
+    """Start the Streamlit application"""
+    print("🚀 Starting Inclusive World Curriculum Assistant...")
+    print("📖 Opening web interface...")
+    print("🌐 The application will open in your default browser")
+    print("⏳ Please wait for the system to load...")
+    print("\n" + "="*50)
+    
+    try:
+        # Start Streamlit
+        subprocess.run([
+            sys.executable, "-m", "streamlit", "run", "app.py",
+            "--server.port", "8501",
+            "--server.address", "localhost"
+        ])
+    except KeyboardInterrupt:
+        print("\n👋 Application stopped by user")
+    except Exception as e:
+        print(f"❌ Error starting application: {e}")
+
+def main():
+    """Main launcher function"""
+    print("🎓 Inclusive World Curriculum Assistant")
+    print("=" * 50)
+    
+    # Check environment
+    if not check_environment():
+        print("\n❌ Environment check failed. Please ensure all files are present.")
+        sys.exit(1)
+    
+    # Check dependencies
+    if not check_dependencies():
+        print("\n❌ Dependencies check failed. Please install required packages.")
+        sys.exit(1)
+    
+    # Start application
+    start_application()
+
+if __name__ == "__main__":
+    main() 

setup.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python3
+"""
+Setup script for Inclusive World Curriculum Assistant
+"""
+
+import os
+import sys
+import subprocess
+import platform
+from pathlib import Path
+
+def check_python_version():
+    """Check if Python version is compatible"""
+    if sys.version_info < (3, 8):
+        print("❌ Error: Python 3.8 or higher is required")
+        print(f"Current version: {sys.version}")
+        return False
+    print(f"✅ Python version: {sys.version}")
+    return True
+
+def check_system_requirements():
+    """Check system requirements"""
+    print("\n🔍 Checking system requirements...")
+    
+    # Check available memory (rough estimate)
+    try:
+        import psutil
+        memory_gb = psutil.virtual_memory().total / (1024**3)
+        print(f"📊 Available RAM: {memory_gb:.1f} GB")
+        if memory_gb < 8:
+            print("⚠️  Warning: Less than 8GB RAM detected. Model loading may be slow.")
+        else:
+            print("✅ Sufficient RAM detected")
+    except ImportError:
+        print("⚠️  psutil not available - cannot check RAM")
+    
+    # Check disk space
+    try:
+        disk_usage = psutil.disk_usage('.')
+        free_gb = disk_usage.free / (1024**3)
+        print(f"💾 Available disk space: {free_gb:.1f} GB")
+        if free_gb < 5:
+            print("⚠️  Warning: Less than 5GB free space. Consider freeing up space.")
+        else:
+            print("✅ Sufficient disk space")
+    except:
+        print("⚠️  Could not check disk space")
+
+def install_dependencies():
+    """Install required dependencies"""
+    print("\n📦 Installing dependencies...")
+    
+    try:
+        # Upgrade pip first
+        subprocess.check_call([sys.executable, "-m", "pip", "install", "--upgrade", "pip"])
+        
+        # Install requirements
+        subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"])
+        print("✅ Dependencies installed successfully")
+        return True
+    except subprocess.CalledProcessError as e:
+        print(f"❌ Error installing dependencies: {e}")
+        return False
+
+def create_directories():
+    """Create necessary directories"""
+    print("\n📁 Creating directories...")
+    
+    directories = ["Slides", "chroma_db"]
+    for directory in directories:
+        Path(directory).mkdir(exist_ok=True)
+        print(f"✅ Created directory: {directory}")
+
+def check_curriculum_files():
+    """Check if curriculum files exist"""
+    print("\n📚 Checking curriculum files...")
+    
+    slides_dir = Path("Slides")
+    if not slides_dir.exists():
+        print("⚠️  Slides directory not found. Creating...")
+        slides_dir.mkdir(exist_ok=True)
+    
+    pdf_files = list(slides_dir.glob("*.pdf"))
+    if pdf_files:
+        print(f"✅ Found {len(pdf_files)} curriculum PDF files:")
+        for pdf in pdf_files:
+            print(f"   📄 {pdf.name}")
+    else:
+        print("⚠️  No PDF files found in Slides directory")
+        print("   Please add your curriculum PDF files to the Slides/ directory")
+
+def create_sample_config():
+    """Create a sample configuration if needed"""
+    print("\n⚙️  Checking configuration...")
+    
+    if not Path("config.py").exists():
+        print("❌ config.py not found. Please ensure it exists.")
+        return False
+    
+    print("✅ Configuration file found")
+    return True
+
+def test_imports():
+    """Test if key modules can be imported"""
+    print("\n🧪 Testing imports...")
+    
+    required_modules = [
+        "streamlit",
+        "langchain",
+        "chromadb", 
+        "transformers",
+        "torch",
+        "fitz"
+    ]
+    
+    failed_imports = []
+    for module in required_modules:
+        try:
+            __import__(module)
+            print(f"✅ {module}")
+        except ImportError:
+            print(f"❌ {module}")
+            failed_imports.append(module)
+    
+    if failed_imports:
+        print(f"\n❌ Failed to import: {', '.join(failed_imports)}")
+        return False
+    
+    print("✅ All required modules imported successfully")
+    return True
+
+def main():
+    """Main setup function"""
+    print("🎓 Inclusive World Curriculum Assistant Setup")
+    print("=" * 50)
+    
+    # Check Python version
+    if not check_python_version():
+        sys.exit(1)
+    
+    # Check system requirements
+    check_system_requirements()
+    
+    # Create directories
+    create_directories()
+    
+    # Check curriculum files
+    check_curriculum_files()
+    
+    # Check configuration
+    if not create_sample_config():
+        sys.exit(1)
+    
+    # Install dependencies
+    if not install_dependencies():
+        print("\n❌ Setup failed. Please check the error messages above.")
+        sys.exit(1)
+    
+    # Test imports
+    if not test_imports():
+        print("\n❌ Some modules failed to import. Please reinstall dependencies.")
+        sys.exit(1)
+    
+    print("\n🎉 Setup completed successfully!")
+    print("\n🚀 To start the application:")
+    print("   streamlit run app.py")
+    print("\n📖 For more information, see README.md")
+
+if __name__ == "__main__":
+    main() 

utils.py

@@ -0,0 +1,83 @@
+"""
+Utility functions for the Inclusive World Curriculum Assistant
+"""
+
+import re
+from typing import List, Dict, Any
+from pathlib import Path
+import fitz
+from config import CURRICULUM_TOPICS
+
+def clean_text(text: str) -> str:
+    """Clean and normalize text content"""
+    # Remove extra whitespace
+    text = re.sub(r'\s+', ' ', text)
+    # Remove special characters that might interfere with processing
+    text = re.sub(r'[^\w\s\.\,\!\?\;\:\-\(\)\[\]\{\}]', '', text)
+    return text.strip()
+
+def extract_curriculum_topics(text: str) -> List[str]:
+    """Extract relevant curriculum topics from text"""
+    found_topics = []
+    text_lower = text.lower()
+    
+    for topic in CURRICULUM_TOPICS:
+        topic_lower = topic.lower()
+        if any(word in text_lower for word in topic_lower.split()):
+            found_topics.append(topic)
+    
+    return found_topics
+
+def create_curriculum_summary(docs: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """Create a summary of processed curriculum documents"""
+    summary = {
+        "total_documents": len(docs),
+        "total_content_length": sum(len(doc.get('content', '')) for doc in docs),
+        "topics_covered": [],
+        "document_types": {}
+    }
+    
+    # Analyze document types
+    for doc in docs:
+        filename = doc.get('filename', '')
+        if 'week' in filename.lower():
+            week_num = re.search(r'week\s*(\d+)', filename.lower())
+            if week_num:
+                summary["document_types"][f"Week {week_num.group(1)}"] = filename
+    
+    # Extract common topics
+    all_content = ' '.join([doc.get('content', '') for doc in docs])
+    summary["topics_covered"] = extract_curriculum_topics(all_content)
+    
+    return summary
+
+def validate_pdf_file(file_path: str) -> bool:
+    """Validate if a file is a readable PDF"""
+    try:
+        doc = fitz.open(file_path)
+        if doc.page_count > 0:
+            doc.close()
+            return True
+        doc.close()
+        return False
+    except Exception:
+        return False
+
+def get_file_info(file_path: str) -> Dict[str, Any]:
+    """Get information about a PDF file"""
+    try:
+        doc = fitz.open(file_path)
+        info = {
+            "filename": Path(file_path).name,
+            "page_count": doc.page_count,
+            "file_size": Path(file_path).stat().st_size,
+            "is_valid": True
+        }
+        doc.close()
+        return info
+    except Exception as e:
+        return {
+            "filename": Path(file_path).name,
+            "error": str(e),
+            "is_valid": False
+        }