sayakpaul / ml-deployment-k8s-fastapi

This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.
https://medium.com/google-developer-experts/load-testing-tensorflow-serving-and-fastapi-on-gke-411bc14d96b2
Apache License 2.0
198 stars 36 forks source link

Find a better way to report the latest API endpoint. #25

Closed sayakpaul closed 2 years ago

deep-diver commented 2 years ago

I guess API endpoint never changes because the Service entity remains as is always

sayakpaul commented 2 years ago

Yes, right.

What about the Cluster External IP? I am talking about this endpoint:

http://{EXTERNAL-IP}:80/predict/image

So, in your opinion, what we have written here is sufficient?

deep-diver commented 2 years ago

Yeah that is my guess

sayakpaul commented 2 years ago

Cool. Closing it then.