gesad-lab / dome

DoME Experiment is a type of no-code tool, that implements a reference architecture for creating information systems from the automated evolution of the domain model, using NLP, Large Language Models and Self Adaptive Systems.
MIT License
2 stars 1 forks source link
gpt gpt-3 gpt-models large-language-models machine-learning nlp nlp-machine-learning prompt-engineering python self-adaptive-systems software-architecture software-engineering

DomE

DomE Experiment is an implementation of a reference architecture for creating information systems from the automated evolution of the domain model. The architecture comprises elements that guarantee user access through automatically generated interfaces for various devices, integration with external information sources, data and operations security, automatic generation of analytical information, and automatic control of business processes. All these features are generated from the domain model, which is, in turn, continuously evolved from interactions with the user or autonomously by the system itself. Thus, an alternative to the traditional software production processes is proposed, which involves several stages and different actors, sometimes demanding a lot of time and money without obtaining the expected result. With software engineering techniques, self-adaptive systems, and artificial intelligence, it is possible, as will be shown, the integration between design time and execution time, obtaining, directly from the user's actions, the necessary data for the evolution of the domain model. The essential artifacts are built from the domain model, making them available, in real-time and with a good level of security, the primary interfaces for data manipulation by the user.

For additional resources for learning about DoME, please access the VISION.md file.

Labelled test dataset

https://drive.google.com/file/d/1IMckKMW5jZDFPXDdv1kJFw0ye2MEiIG7/view?usp=sharing

Installation

Setup the follow environment variables:

DOME_TELEGRAM_TOKEN=telegram_bot_token
HUGGINGFACE_TOKEN=huggingface_token
OPENAI_API_KEY=openai_api_key

Install Microsoft C++ Build Tools

https://visualstudio.microsoft.com/visual-cpp-build-tools/

For uses a GPU, install CUDA Toolkit:

https://developer.nvidia.com/cuda-downloads

Credits

This project is linked with the Master's Degree Program of the University of State of Ceará (http://www.uece.br/ppgcc/).
Project Supervisor: PhD Paulo Henrique Maia (https://gesad.github.io/team/paulo-henrique/)
Student: Anderson Martins Gomes (https://www.linkedin.com/in/amartinsg/)