ferraridg / async-ml-inference

PoC with FastAPI and Celery to ML inference

Hey, I'm Daniel

I work as a machine learning engineer. I'm eager to learn, enjoy sharing and debating, and I'm always ready to cooperate. I have an enthusiasm for mentoring and helping people grow in their careers.

DLite

A group of friends came together to share ideas and build tools. So, we created DLite.

Tech that I work with

Where can you find me

async-ml-inference's Issues

Publishing Documentation

Have an HTML page with documentation from code pushed via CI/CD

https://tech.michaelaltfield.net/2020/07/18/sphinx-rtd-github-pages-1/
https://tech.michaelaltfield.net/2020/07/23/sphinx-rtd-github-pages-2/

Use rq/arq workers

Implement an alternative to the Celery backend to decrease complexity and try to solve the results consumer issue.

Read:

• https://python-rq.org/
• https://arq-docs.helpmanual.io/

Background task

Thanks for sharing,
Is the use of background task is not a compromise in this case?

Enhance documentation

Hey @FerrariDG!

Would love to see more documentation around future roadmap, backlog of issues and contributing guidelines.

Willing to help out with that as well, do let me know!

Best,
@chtnnh