🧠 AI Code Decoder (Reliable Edition)

A robust Python code analysis tool powered by AI that provides intelligent code explanations, quizzes, and structural analysis with automatic fallback between multiple AI providers.

✨ Features

• Multi-Provider AI Support: OpenAI, Anthropic Claude, and Ollama with automatic fallback
• Safe JSON Parsing: Robust error handling and timeout management
• Interactive Web Interface: Built with Streamlit for easy code analysis
• Code Structure Analysis: Automatic detection of functions, classes, imports, and lines
• Study Modes:
  • Explanation only
  • Explanation with quiz
  • Quiz only
• Flexible Input: Paste code directly or upload Python files
• Configurable Settings: Adjustable temperature, detail levels, and custom instructions
• Health Checks: Automatic provider availability detection

🏗️ Project Structure

ai-code-decoder/
├── app.py                    # Main Streamlit application
├── requirements.txt          # Python dependencies
├── README.md                # This file
├── config/
│   └── settings_example.toml # Configuration template
└── core/
    ├── __init__.py          # Package initialization
    ├── ai_providers.py      # AI provider integrations
    └── analysis_utils.py    # Code analysis utilities

🚀 Installation & Setup

Prerequisites

• Python 3.8 or higher
• pip package manager

1. Clone the Repository

git clone https://github.com/vinupalackal/ai-code-decoder.git
cd ai-code-decoder

2. Create Virtual Environment (Recommended)

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install Dependencies

pip install -r requirements.txt

4. Configure API Keys (Optional)

You can provide API keys either through the web interface or environment variables:

Environment Variables:

export OPENAI_API_KEY="your_openai_api_key_here"
export ANTHROPIC_API_KEY="your_anthropic_api_key_here"

Configuration File (Optional):

cp config/settings_example.toml config/settings.toml
# Edit settings.toml with your preferences

🎯 Usage

Running the Application

streamlit run app.py

The application will start and be available at http://localhost:8501

Using Different AI Providers

OpenAI

1. Select "openai" from the Provider dropdown
2. Enter your API key in the sidebar (or set OPENAI_API_KEY environment variable)
3. Choose a model (default: gpt-4o-mini)

Ollama (Local AI)

1. Install and start Ollama: https://ollama.ai
2. Pull a model: ollama pull llama3.1
3. Select "ollama" from the Provider dropdown
4. Ensure Ollama URL is correct (default: http://localhost:11434)

Anthropic Claude

1. Select "anthropic" from the Provider dropdown
2. Enter your Anthropic API key
3. Choose a model (default: claude-3-5-sonnet-latest)

Analysis Workflow

1. Input Code: Paste Python code or upload a .py file
2. Configure Settings:
   • Choose AI provider and model
   • Set detail level (low/medium/high)
   • Select study mode
   • Adjust temperature for creativity
3. Review Code Stats: View automatic structural analysis
4. Generate Analysis: Click "Run" to get AI-powered explanation

🔧 Configuration Options

Detail Levels

• Low: Brief, high-level overview
• Medium: Balanced explanation with key concepts
• High: Comprehensive, detailed analysis

Study Modes

• Explanation Only: Pure code explanation
• Explanation + Quiz: Explanation followed by comprehension questions
• Quiz Only: Direct quiz generation for testing understanding

Temperature Settings

• 0.0-0.3: More focused, deterministic responses
• 0.4-0.7: Balanced creativity and consistency
• 0.8-1.0: More creative, varied responses

🛠️ Development

Running in Development Mode

# Install development dependencies
pip install streamlit

# Run with auto-reload
streamlit run app.py --server.runOnSave true

Code Structure

• app.py: Main Streamlit interface and user interaction logic
• core/ai_providers.py: AI provider implementations with fallback logic
• core/analysis_utils.py: Code parsing and structural analysis
• config/settings_example.toml: Default configuration template

🔍 Troubleshooting

Common Issues

1. Ollama Connection Failed

   • Ensure Ollama is running: ollama serve
   • Check if the URL is correct (default: http://localhost:11434)
   • Verify you have models installed: ollama list

2. OpenAI API Errors

   • Verify API key is valid
   • Check account usage limits
   • Ensure model name is correct

3. File Upload Issues

   • Only Python (.py) files are supported
   • Files must be UTF-8 encoded
   • Check file size limits

Getting Help

• Check the application logs in the terminal
• Verify all dependencies are installed
• Ensure API keys have proper permissions

📝 License

This project is open source. See the repository for license details.

🤝 Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

---

Made with ❤️ for better code understanding