cadCAD GPT is an open-source LLM agents framework to support token systems simulations. cadCAD GPT can be used on top of any Python model following the cadCAD/radCAD model structure. Via Python functions, it can integrate today’s most powerful data analysis and machine learning libraries (Tools) and can access data in various formats (Memory). Finally, cadCAD GPT allows users to control and track the agents’ workflow for verifiable and reproducible results.
Learn more about cadCAD GPT in this series of articles:
- Part I: Hello, cadCAD GPT! Requirements and conceptual design of LLMs to support token system simulations
- Part II: This is me, cadCAD GPT! A deep-dive into cadCAD GPT’s powerful, customizable components
- Part III: Let’s chat! Experiments and further development of cadCAD GPT
- Installation
- Quickstart
- Contributing
- Community and Support
- Future Additions
- License
- Acknowledgements
- Citations
- Links
Include instructions on how to download, install dependencies, and set up the project. This could include:
- How to download the project files:
git clone https://github.com/TE-Academy/cadCAD-GPT.git - Installation of dependencies:
or just run the setup.ipynb file which will install the requirements for you.
pip install -r requirements.txt
- In the examples folder, open the 0_template_folder. This has all the components to get started building your own chatbot.
- Copy your radcad code into the example_radcad.py file.
- Go to the example_project.ipynb file, paste your openAI key in the openai_key variable and run all the code. And you can start chatting with the cadcad_gpt chatbot now in this notebook.
Guidelines for contributors:
- Instructions on how to contribute (TBD).
- Code styling conventions (write about pep257 format here).
- Contribution process (TBD).
For any ideas, discussions or queries join the TE Academy Discord!
You'll find us in the "build" category at TE Academy's Discord:
- Due to its highly modular design, cadCAD GPT can be customized and expanded. To learn more about tools and memory features we aim to implement next, check out "cadCAD GPT Further Expansions" in this article.
- In this early stage of LLMs applied to token engineering, many intriguing questions emerge. We've collected a number of open research questions, please reach out in case you are interested to collaborate and contribute.
This project is licensed under the MIT License - see the LICENSE file for details.
To demonstrate cadCAD GPT accessing a Python system model, we're using @danlessa's radCAD version of the Predator-Prey model. radCAD is a Python framework for modelling and simulating dynamical systems, open-sourced by cadLabs. It is inspired by and compatible with cadCAD, the open-source open-source Python package that assists in the processes of designing, testing and validating complex systems through simulation.
cadCAD GPT was kickstarted by funding received from Token Engineering Commons. We thank the TE Commons community, and Gideon Rosenblatt in particular, who encouraged us to embark on this exciting journey. Big thank you to our advisors Roderick McKinley, Richard Blythman, and Robert Koschig for ongoing support and feedback. Shoutout to Dr. Achim Struve, Dimitrios Chatzianagnostou, Stephanie Tramicheck, Ivan Bermejo, Rohan Sundar, and Lukasz Szymanski for the most valuable alpha user feedback and insights, and Kaidlyne Neukam for her tireless support in publishing this work.
If you find cadCAD GPT useful, please consider citing the project:
@software {cadCAD GPT,
author = Rohan Mehta, Angela Kreitenweis,
license = MIT License,
month = Nov,
title = cadCAD GPT - an LLM agents framework to support token systems simulations,
url = https://github.com/TE-Academy/cadCAD-GPT,
year = 2023
}
Learn more about TE Academy, attend our events and study token engineering!
Web https://tokenengineering.net
YouTube https://www.youtube.com/c/tokenengineering
Discord https://discord.gg/te-academy
Twitter https://twitter.com/tokengineering
Subscribe to our newsletter for the latest trends, and #tokenengineering news!
