Seldon Vectorize Field Stage
The Seldon Vectorize Field stage invokes a machine learning model to encode a string field to a vector representation.
|
|
This feature is only available in Managed Fusion 5.9.5.
|
|
|
When entering configuration values in the UI, use unescaped characters, such as \t for the tab character. When entering configuration values in the API, use escaped characters, such as \\t for the tab character.
|
Invokes a seldon machine learning model to encode a string field to a vector representation. Will be skipped if the field to encode doesn't exist or is null on the pipeline document.
skip - boolean
Set to true to skip this stage.
Default: false
label - string
A unique label for this stage.
<= 255 characters
condition - string
Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.
modelId - stringrequired
Model ID of the model to use for encoding. Only models which accept a single string parameter and return a single dense vector value per input are supported.
modelInputFieldName - stringrequired
Name to specify for the input parameter when sending the text to encode to the chosen ML model
Default: text
modelOutputVectorFieldName - stringrequired
The name of the field in the ML model response that contains the vector encoding.
Default: vector
failOnError - boolean
Flag to indicate if this stage should throw an exception if an error occurs while generating a prediction for a document.
Default: false
sourceFieldName - stringrequired
Name of the string field whose value should be submitted to the ML model for encoding. If the field doesn't exist or is null in the pipeline document, this stage will be skipped.
destinationFieldName - stringrequired
Name of the field into which the dense vector value from the ML model response will be saved.