Lucidworks AI Vectorize FieldLucidworks AI
|
|
This article describes a beta feature
This is draft documentation for a feature in our beta program. Documentation for this feature may contain outdated or inaccurate information. This article will not appear in search results.
Consult with your Lucidworks representative for any questions or comments about the feature. To leave feedback about the documentation, click the Feedback button and follow the prompts.
|
Lucidworks AI Vectorize Field is a Fusion index pipeline stage that invokes a Lucidworks AI model to encode a string field to a vector representation.
To use this stage, non-admin Fusion users must be granted the POST:/LWAI-ACCOUNT-NAME/** permission in Fusion, which is the Lucidworks AI API Account Name defined in the Lucidworks AI Gateway service when this stage is configured.
|
|
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 Lucidworks AI 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.
accountName - stringrequired
ML Platform API Account Name as defined in AI Gateway Service
modelType - stringrequired
ML Platform API model to use for encoding, for example 'multilinguallm'. 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 model
Default: text
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 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 model response will be saved.