Repository files navigation

A powerful tool for analyzing, documenting, and visualizing SQL codebase structure and dependencies. This project combines modern language models with vector storage to provide comprehensive insights into SQL code architecture.

• Intelligent SQL Parsing: Automatically breaks down SQL files into logical chunks (packages, procedures, functions)
• Dependency Analysis: Identifies and visualizes relationships between different SQL objects
• Vector-Based Storage: Uses ChromaDB for efficient storage and retrieval of code chunks
• LLM-Powered Analysis: Leverages language models to provide detailed code analysis and insights
• Interactive Documentation: Generates comprehensive HTML documentation with interactive components
• Streamlit Interface: User-friendly web interface for uploading and analyzing SQL files
• **Monolithic helps to generate a SQL file which can then be used for this project
• **Output is created as a HTML , sample shown sql_documentation.html

The project consists of several key components:

• sqldataeng.py: SQL parsing and chunk extraction
• vectorstore.py: Vector storage implementation using ChromaDB
• llmprocessor.py: Language model integration for code analysis
• docgenerator.py: Documentation generation and formatting
• main.py: Streamlit web interface

• Python 3.8+
• CUDA-capable GPU (optional, for faster processing)

1. Clone the repository:

git clone https://github.com/ramcovasu/monolithic.gitcd monolithic

2. Create a virtual environment:

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

3. Install dependencies:

pip install -r requirements.txt

1. Start the Streamlit application:

streamlit run main.py --server.fileWatcherType none

2. Open your browser and navigate tohttp://localhost:8501

3. Upload your SQL file through the web interface

4. Follow the step-by-step process:

   • Parse SQL code
   • Process and store chunks
   • Generate analysis
   • View and download documentation

• Intelligent package and procedure detection
• Accurate dependency tracking
• Support for complex SQL structures

• Efficient code chunk storage
• Semantic similarity search
• Dependency graph construction

• Comprehensive HTML reports
• Interactive visualizations
• Detailed code analysis
• Dependency diagrams

• Uses BAAI/bge-small-en-v1.5 for embeddings
• Supports GPU acceleration when available
• Efficient batch processing

• ChromaDB for persistent storage
• Optimized for code similarity search
• Efficient metadata handling

• Local LLM support via LM Studio
• Batched processing for large codebases
• Error handling and retry logic

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• ChromaDB for vector storage
• Sentence Transformers for embeddings
• Streamlit for the web interface
• SQLParse for SQL parsing

monolithic/├── main.py              # Streamlit application├── sqldataeng.py       # SQL parsing engine├── vectorstore.py      # Vector storage management├── llmprocessor.py     # LLM integration├── docgenerator.py     # Documentation generator├── requirements.txt    # Project dependencies└── README.md          # This file

• Support for additional SQL dialects
• Enhanced visualization options
• Code quality metrics
• Performance optimization suggestions
• Batch processing for multiple files

Create an issue in the repository for bug reports, feature requests, or general questions.