If specified, will assume that MLmodel/MLproject is running within a Conda environment with the necessary dependencies for the current project instead of attempting to create a new conda environment. t, -content-type Ĭontent type of the input file. o, -output-path įile to output results to as json file. For more information about supported remote URIs for model artifacts, see -i, -input-path ĬSV containing pandas DataFrame to predict against. A local path, a ‘runs:/’ URI, or a remote storage URI (e.g., an ‘s3://’ URI). enable-mlserverĮnable serving with MLServer through the v2 inference protocol. The version of installed mlflow will be the same as the one used to invoke this command. If specified and there is a conda or virtualenv environment to be activated mlflow will be installed into the environment after it has been activated. virtualenv: use virtualenv (and pyenv for Python version management) If specified, create an environment for MLmodel/MLproject using the specifiedĮnvironment manager. Name to use for built image -env-manager For more information about supported remote URIs for model artifacts, see -n, -name For more information about supported remote URIs for model artifacts, see -f, -flavor This will be auto inferred if it’s not given See all supported deployment targets and installation Support is currently installed for deployment to: sagemaker More details on the supported URI format and config options Required Name of the deployment -t, -target See documentation/help for your deployment target for a list of supported config options. These tags are added to a set of default tags that include the model path, the model run id (if specified), and more.Įxtra target-specific config for the model deployment, of the form -C name=value. t, -tags Ī collection of tags, represented as a JSON-formatted dictionary of string key-value pairs, to associate with the Azure Container Image and the Azure Model that are created. d, -description Ī string description to associate with the Azure Container Image and the Azure Model that are created. If unspecified, a unique image name will be generated. The name to assign the Azure Model that is created. The name to assign the Azure Container Image that is created.
The subscription id associated with the Azure Workspace in which to build the image -i, -image-name Required The name of the Azure Workspace in which to build the image. For more information about supported remote URIs for model artifacts, see -w, -workspace-name
0 kommentar(er)
