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
I Deployed A Model With:

I deployed a model with:

clearml-serving \ --id 875de894b62144a7949e471532728809 \ model add \ --engine "xgboost" \ --endpoint "best_model" \ --preprocess "test_preprocess.py" \ --name "best_model" \ --project "<name>" \ --model-id "ef5c6a281a8147adadcb92c54bbd4caf"Its here:
clearml-serving --id 875de894b62144a7949e471532728809 model list clearml-serving - CLI for launching ClearML serving engine List model serving and endpoints, control task id=875de894b62144a7949e471532728809 Info: syncing model endpoint configuration, state hash=bd45d8a56a9f7cac1007e32145c56110 Endpoints: { "best_model": { "engine_type": "xgboost", "serving_url": "best_model", "model_id": "ef5c6a281a8147adadcb92c54bbd4caf", "version": "", "preprocess_artifact": "py_code_best_model", "input_size": null, "input_type": null, "input_name": null, "output_size": null, "output_type": null, "output_name": null, "auxiliary_cfg": null } }but when I call it with
curl -X POST \ " " \ -H "accept: application/json" \ -H "Content-Type: application/json" \ -d '{"x0": 1, "x1": 2}'result is:
{"detail":"Error processing request: Model inference endpoint 'best_model' not found"}

  
  
Posted one year ago
Votes Newest

Answers 12


yes, I do, I added a auxiliary_cfg and I saw it immediately both in CLI and in the web ui

  
  
Posted one year ago

yes, I do, I added a

auxiliary_cfg

and I saw it immediately both in CLI and in the web ui

How many Tasks do you see in the UI in DevOps project with the system Tag SERVING-CONTROL-PLANE ?

TBH our Preprocess class has an import in it that points to a file that is not part of the preprocess.py so I have no idea how you think this can work.

ConvolutedSealion94 actually you can add an entire folder as preprocessing, including multiple files
See example description here:
https://github.com/allegroai/clearml-serving/releases/tag/1.1.0

  
  
Posted one year ago

Hmm seems like everything is working, can you check in the UI if you see the serving session ID in the DevOps project? maybe there are two, and you configured one an dthe docker-compose is running another ?

  
  
Posted one year ago

TBH our Preprocess class has an import in it that points to a file that is not part of the preprocess.py so I have no idea how you think this can work.

  
  
Posted one year ago

Hi ConvolutedSealion94
Just making sure, you spinned the docker-compose of the clearml serving as well ?

  
  
Posted one year ago

I guess so, this was done by our DevOps guy and he said he is following instructions

  
  
Posted one year ago

Is there any restriction on what can be in preprocess.py?

  
  
Posted one year ago

Is there a more detailed logging about what's going on?

  
  
Posted one year ago

Is it possible that the Prerocess class is the problem?

  
  
Posted one year ago

This is very different than from in the xgboost example:

  
  
Posted one year ago
590 Views
12 Answers
one year ago
one year ago
Tags