I am completely stuck with the serving.
I did the custom example. I see the endpoint in clearml-serving -id ... model list and it replies
{"detail":"Error processing request: Model inference endpoint 'test_model_custom' not found"}
Can you confirm that this is the right URL:
curl -X POST " http://127.0.0.1:8080/serve/test_model_custom " -H "accept: application/json" -H "Content-Type: application/json" -d '{"features": [1, 2, 3]}'
if I change anything with the URL:{"detail":"Not Found"}
Any different port and connection is refused.
Hi ConvolutedSealion94
Yes this seems like the correct curl
How did you spin the clearml-serving containers? is it with the docker-compose or with the helm chart (I remember that there are some pitfalls with the helm chart, and I would actually start with the local docker-compose to debug it)
Apparently our devops guy figured it out that you needed to have a different port number and a different docker container given 8080 was already occupied
