Validation error ``ML Backend health check failed''

Label Studio Support
,
1

Question:

My ml backend is up and running but still I am not able to connect it with my label studio.
Both ml backend and label studio running on docker.
image

image (1)
image (1)932×490 19.6 KB

Answer:

Try using the following url: http://host.docker.internal:9090

host.docker.internal is used to access the host from within a docker container. This is necessary because your machine learning backend and Label Studio are running in their own separate docker containers. By using http://host.docker.internal:9090 , you’re telling Label Studio to look for the ML backend on the same machine but outside of its own container.

2

Same problem as above, but running on directly on linux, no docker.
Validation error

  • Can’t connect to ML backend http://localhost:9090, health check failed. Make sure it is up and your firewall is properly configured. Learn more about how to set up an ML backend. Additional info: HTTPConnectionPool(host=‘localhost’, port=9090): Max retries exceeded with url: /health (Caused by NewConnectionError(‘: Failed to establish a new connection: [Errno 111] Connection refused’))

Version: 1.13.2.dev0

Also, it was working a couple hours ago, and all of a sudden I can’t connect anymore. Restarted the ml backend and label studio several times, but no luck.

1 Like
3

I had the same problem with non-docler ML backend.
I had to start label studio first with
label-studio start
and only later start the ml backend with
label-studio-ml start segment_anything_2_image

I guess the http://localhost:9090 was occupied somwhow.
Also check your ml-model page by refreshing the page, so it is up.
Terveisin, Markus