We have a team that would like to use Ray serve to set up an ecosystem of models behind a web app. We are having difficulty getting a deployment for local development. When we try to use docker-compose with ray images we run into problems that the ray image python version (3.7) is not compatible …

Can you change serve.start(detached=True) to serve.start(detached=True, http_options={"host": "0.0.0.0"}? This should expose your deployment publicly, so you can access it using http://$RAY_HEAD_SERVICE_HOST:8000/api1. There’s more info in this documentation .

For anyone in the future interested we use this setup for local development. A docker compose file: services: # bunch of other containers ray-head: image: ray_head container_name: ray-head build: context: ./ dockerfile: packagename/deployments/ray_head/Dockerfile po…

The code above saved me hours of figuring everything out myself, much appreciated!

What is best practice for local setup?

Ray Serve

Joshuaalbert June 16, 2022, 7:12pm 3

That was the solution. Thank you! With this was able to dockerise the setup and gain access.

Topic		Replies	Views
Example docker compose to run RayServe app Ray Serve	1	107	December 23, 2025
Can't access ray server outside docker container Ray Serve	1	321	July 31, 2024
How to correctly build a Ray Serve server in Docker with a generic Ubuntu image (x86_64 in an amd system)? Ray Serve	4	438	April 24, 2025
Unable to run FastAPI Ray Serve Deployment Example Ray Serve	3	1302	August 4, 2022
[Medium] Using docker image for service deployment Ray Serve	7	1033	December 29, 2023

What is best practice for local setup?

Related topics