CodeQA

CodeQA is a command-line tool that helps you semantically search and analyze your codebase. It uses advanced language models to understand code context and generate meaningful responses about your code.

Features

• 🔍 Semantic code search using embeddings
• 📝 Interactive query mode
• 🌲 Project structure awareness
• 📋 LLM-ready prompt generation
• 🎯 Smart file selection for context
• 🚀 GPU/MPS acceleration support

Dependencies

The project requires Python 3.11+ and the following main dependencies:

chromadb>=0.4.22
torch>=2.0.0
transformers>=4.30.0
pathspec>=0.11.2
numpy
tqdm>=4.65.0
pyperclip

Installation

1. Clone the repository:

git clone https://github.com/yourusername/codeqa.git
cd codeqa

2. Create and activate a virtual environment:

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

3. Install dependencies:

pip install -r requirements.txt

Usage

Basic usage:

python main.py --dir /path/to/your/codebase

Command Line Options

• --dir: (Required) Path to the codebase directory to analyze
• --db-path: Path to store embeddings database (default: "code_embeddings")
• --n: Number of top results to return (default: 5)
• --debug: Enable debug logging
• --show-content: Show file contents in results
• --code-extensions: List of file extensions to include (e.g., ".py .js .ts")
• --full-path: Show full file paths in results
• --copy-prompt: Enable prompt generation and copying to clipboard

Interactive Mode

After starting the tool, you can:

1. Enter your queries about the codebase
2. View matched files with relevance scores
3. When using --copy-prompt:
   • Select specific files to include in the context
   • Get token count for the generated prompt
   • Have the prompt automatically copied to clipboard

Examples

Search for file handling code:

python main.py --dir ./myproject
> how does the file reading work

Generate an LLM-ready prompt:

python main.py --dir ./myproject --copy-prompt
> explain the authentication system

Analyze specific file types:

python main.py --dir ./myproject --code-extensions .py .ts .js

Project Structure

codeqa/
├── main.py              # Main entry point
├── utils/
│   └── file_utils.py    # File handling utilities
├── embeddings/
│   └── embedder.py      # Code embedding generation
├── tokenization/
│   └── chunker.py       # Code chunking logic
└── models/
    └── code_chunk.py    # Data models

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

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