CodebookAI is a tool designed to assist qualitative researchers in processing large datasets through OpenAI's GPT models (e.g., 4o, 5, o3, etc.). Its Task Builder lets you write your own prompt against an imported table, define named label Lists that constrain the model's response to on-list values only (no hallucinated or reworded labels to clean up), and choose exactly which columns -- including existing IDs -- carry through to your results. Run a task live for quick results or submit it as a batch for large, cost-effective jobs. The app also includes a variety of other tools aimed at qualitative data preparation and analysis.
- Download the latest .exe (Get one here). This is a standalone application that does not require installation. Just double-click to run. Only tested on Windows 10.
- CodebookAI required you to supply an OpenAI API key in the Settings (File > Settings) (Get one here). This keeps CodebookAI open-source and free to use. You control your own API key and are responsible for any costs incurred through your usage of OpenAI's services.
- Not sure what CodebookAI can do? Check out the Example section.
The repository includes an automated test suite that runs without a live OpenAI API key or a graphical display.
# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt
# Run all tests
pytestContinuous integration is configured via GitHub Actions (.github/workflows/tests.yml)
and runs on every push and pull request across Python 3.10, 3.11, and 3.12.
See CONTRIBUTING.md for a full guide on setting up a local development environment, the project structure, coding conventions, and how to submit changes.
If you find this tool helpful, consider supporting its development by buying me a coffee!
This project is licensed under the MIT License. Please ensure compliance with OpenAI's usage policies when using this application.
This application requires an OpenAI API key and will incur costs based on your usage. Batch processing typically offers significant cost savings compared to individual API calls. Please monitor your usage and costs through the OpenAI dashboard.
Additionally, not all GPT models have been tested and may not work with this software. At this time, the models that have been tested are gpt-4o, gpt-4o-mini, and gpt-5.