Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Monitoring Related Question

monitoring related question                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             Good evening everyone,

I followed the below documentation to implement the clearml monitoring using prometheus and grafana
None

I ran the docker compose file which is provided with prometheus , grafana , clearml-serving-inference, kafka

Configured below variables in env file
CLEARML_SERVING_TASK_ID=<service_id>
CLEARML_SERVING_POLL_FREQ=1

trained the sklearn model
able to get the response with the below curl command
curl -X POST " None " -H "accept: application/json" -H "Content-Type: application/json" -d '{"x0": 1, "x1": 2}'

But i am not seeing the metrics in clearml-inference-stats job configured in the prometheus.yml, Not sure what i am missing. Need help on the same.

  
  
Posted 9 months ago
Votes Newest

Answers 3


Hi @<1607909176359522304:profile|UnevenCow76>

followed the below documentation to implement the clearml monitoring using prometheus and grafana

Did you try following this example, it includes both deploying a model and adding grafana metrics:
None

  
  
Posted 9 months ago

Hi @<1607909176359522304:profile|UnevenCow76> , I suggest you review the following video on serving - None

This also explains how to visualize different metrics in Grafana

  
  
Posted 9 months ago

@<1523701205467926528:profile|AgitatedDove14> and @<1523701070390366208:profile|CostlyOstrich36> Thanks for the quick response, I went through the video and documentation, Order in which i am executing the steps were in correct, Issue is resolved now.

  
  
Posted 9 months ago
497 Views
3 Answers
9 months ago
9 months ago
Tags