Score ML Models
This set of handlers provide ability to run real-time inference using various machine learning libraries, which share the same set of parameters and actions.
Last updated
This set of handlers provide ability to run real-time inference using various machine learning libraries, which share the same set of parameters and actions.
Last updated
This handler is .
model.state
Name of the state manager with model configurations
model
-
model.id
Id of the model to run on this instance
recommendation
-
model.store.system
Name of the system to store model assets
hdfs_default
-
model.local.dir
Local directory to store model assets for execution
/tmp
java.io.tmpdir
Scores input data using pretrained model managed by this handler. Event metadata fields applicable for this action are as follows:
inputElement
Json path for the input in request event payload
parameters
-
outputElement
Json path for the output in response event payload
$.score
-
With event metadata parameters as:
inputPattern
JMESPath pattern to apply on data input
[ [text] ]
-
outputPattern
JMESPath pattern to apply on data output, before returning response
{totalPrice:basket.totalPrice}
-
This handler (com.rierino.handler.tensor.TensorScoreEventHandler) uses library for inference using saved models.
This handler requires the following dependency added to :
This handler (com.rierino.handler.onnx.OnnxScoreEventHandler) uses library for inference using models saved using this common format.
This handler requires the following dependency added to :
This handler (com.rierino.handler.pmml.PMMLScoreEventHandler) uses formatted models for inference.
This handler requires the following dependency added to :
This handler (com.rierino.handler.opennlp.OpenNLPScoreEventHandler) uses library for inference using common NLP tools, saved dictionaries and models.
This handler requires the following dependency added to :