Edit on GitHub


Apply a deployed-model (possibly remotely) to data. The results will be saved as a MLEM Object to output if provided. Otherwise, it will be printed to stdout.


usage: mlem apply-remote [--raw] [-d <path>] [-p <path>]
                         [--rev <commitish>] [-o <path>]
                         [--tp <path>] [-m <text>] [--json]
                         [-f <text>] [-h]
                         [<client> [client options] | --load <declaration>]

Builtin clients:
- http
- rmq
- sagemaker


Models which are deployed somewhere remotely or are being served locally, can have their methods called using the apply-remote command. This command is similar to apply, with the only difference being the model is deployed remotely using a deployment, or served locally. To access the methods of the served model, a client is needed. Currently, the available clients are http and rmq - which are used to launch requests against the fastapi and rmq server types, correspondingly.


  • --raw <boolean> - Pass values as-is without serializers [default: False]
  • -d <path>, --data <path> - Path to MLEM dataset [required]
  • -p <path>, --project <path> - Path to MLEM project [default: (none)]
  • --rev <commitish> - Repo revision to use [default: (none)]
  • -o <path>, --output <path> - Where to save model outputs
  • --tp <path>, --target-project <path> - Project to save target to [default: (none)]
  • -m <text>, --method <text> - Which model method is to be applied [default: predict]
  • --json - Output as json
  • -f <text>, --file_conf <text> - File with options for client in format field.name=path_to_config
  • -h, --help - Show this message and exit.

Example: Apply a locally hosted model to a local dataset

Given a hosted model server (see serve example as a way to easily do this) and a local MLEM dataset mydataset, run the following command to infer the entire dataset with the model and save the output result to myprediction

$ mlem apply-remote http mydataset --host="" --port=3000 --output myprediction

­čÉŤ Found an issue? Let us know! Or fix it:

Edit on GitHub

ÔŁô Have a question? Join our chat, we will help you:

Discord Chat