Does Ray Dashboard support sending sample requests to the local server

[Renyu]

• High: It blocks me to complete my task.

Hi I am trying to set up a ML serving infra and am comparing between Ray Serve and BentoML. Does Ray dashboard support sending sample requests through the dashboard like the localhost:3000 dashboard in BentoML (see figure below)? I can find the similar functionality on the Ray Dashboard. Thanks!

[Huaiwei_Sun]

This is the swagger UI. If you use fastAPI + Ray Serve, it should come with fastAPI automatically.

You can check out fastAPI docs here: Features - FastAPI.

usually it’s running on localhost:8000

[Renyu]

Oh I see. Thanks for the pointer!