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
Hello, Is There Any Hope To Use Clearml-Serving Without The Clearml Server? The Tutorial And Docs Make It Seem Like It'S Required But I Wanted To Check To Be Sure. I Really Like All The Features That Clearml Provides But It Seems Like Everything Is Deep

hello, is there any hope to use clearml-serving without the clearml server? The tutorial and docs make it seem like it's required but I wanted to check to be sure. I really like all the features that clearml provides but it seems like everything is deeply coupled and difficult to mix and match with other tools (orchestration, experiment tracking, model registry, etc...)

  
  
Posted one year ago
Votes Newest

Answers 8


Without the core server

  
  
Posted one year ago

Hi @<1599211868868579328:profile|StalePigeon24> , you do need to have a ClearML server running to use the serving. However, ClearML is super modular so you don't really need to use the various modules to use the serving, it's enough just to spin the server up and have a model registered to start serving it.

Into what difficulties did you run into in regards to the ClearML server?

  
  
Posted one year ago

The install was easy . I really like the local dev setup . Only issue was port conflicts . Not sure why serving and the core server are set to have the same ports 8080

  
  
Posted one year ago

The docs also are a little confusing in that part of them have you setup serving in docker compose but in the tutorial it launches serving in standalone container

  
  
Posted one year ago

I’d really prefer it was modular enough to use serving with any model registry

Oh that's interesting. To serve a model from MLflow, would you have to copy it over to ClearML first?

  
  
Posted one year ago

But in terms of serving, I’d really prefer it was modular enough to use serving with any model registry

  
  
Posted one year ago

Oh the other issue I had was the setup used localhost and I had to change it to my real hostname so that name resolution would function across different docker compose (core , serving)

  
  
Posted one year ago

The assumption is that the server and serving don't run on the same machine. The ClearML server is just a control plane whereas the serving solution actually does computation.

  
  
Posted one year ago
949 Views
8 Answers
one year ago
one year ago
Tags