This project serves as a platform for embedded hardware programming using Large Language Models. It utilizes GraphRAG, PlatformIO, and Ollama to enable local LLM-assisted embedded development.
ollama serve
- Write
abah
in the terminal to start the application.
Run the following:
- Ensure your environment has Python 3.12 installed.
- In the same directory as the
pyproject.toml
file, run:`pip install -e .`
`ollama pull qwen3:30b-instruct`
`ollama pull qwen3-embedding:4B`
- Author: John Abah
- Email:
[john.abah@stud.hshl.de](mailto:john.abah@stud.hshl.de) - LinkedIn:
[https://www.linkedin.com/in/john-abah-311ab233a/](https://www.linkedin.com/in/john-abah-311ab233a/)
- Support the project:
[https://buymeacoffee.com/johnabah](https://buymeacoffee.com/johnabah)