Deployment state#
The state of a deployment corresponds to the state of the predictor configured in it.
Note
Currently, only one predictor is supported in a deployment. Support for multiple predictors (the inference graphs) is coming soon.
Retrieval#
get_state#
Deployment.get_state()
Get the current state of the deployment
Returns
PredictorState. The state of the deployment.
Properties#
available_predictor_instances#
Available predicotr instances.
available_transformer_instances#
Available transformer instances.
condition#
Condition of the current state of predictor.
deployed#
Whether the predictor is deployed or not.
hopsworks_inference_path#
Inference path in the Hopsworks REST API.
internal_port#
Internal port for the predictor.
model_server_inference_path#
Inference path in the model server
revision#
Last revision of the predictor.
status#
Status of the predictor.
Methods#
describe#
PredictorState.describe()
Print a description of the deployment state
to_dict#
PredictorState.to_dict()