Transforming academic papers into functional code.
Paper2Code is an open-source software project that implements a CrewAI system capable of generating code based on computational science academic papers. The system is planned to replicate findings, satisfy specified conditions, and continuously improve its output through self-testing and assessment.
- Parse and analyze computational science papers
- Generate code that satisfies conditions specified in input documents
- Self-testing and continuous improvement capabilities
- Docker integration for easy deployment and execution
- Comprehensive documentation and ethical guidelines
- Python 3.12+
- Docker and Docker Compose
- Make (for using the Makefile)
Note: While Paper2Code is tested and maintained for Python 3.12+, it may work on previous versions. However, we recommend using Python 3.12+ for the best experience and support.
-
Clone the repository:
git clone https://github.com/AIA4S/Paper2Code.git cd Paper2Code -
Set up a virtual environment:
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate` -
Install dependencies:
pip install -r requirements.txt -
Build and run the Docker containers:
docker-compose up --build -
Run the main application:
python src/main.py
To generate code from a paper or requirements document:
python src/main.py --input path/to/your/document.pdf
For more detailed usage instructions, please refer to the User Guide.
We welcome contributions! Please see our Contributing Guidelines for more details.
Full documentation is available in the docs/ directory:
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
If you have any questions or feedback, please open an issue on this repository.
Paper2Code - Transforming academic papers into functional code.