Product Selector

Fusion 5.12
    Fusion 5.12

    LWAI Vectorize QueryLucidworks AI

    Table of Contents

    Lucidworks AI Vectorize Query is a Fusion query pipeline stage that generates a vector based on the current query string (q parameter).

    This feature is currently only available to clients who have contracted with Lucidworks for features related to Neural Hybrid Search and Lucidworks AI.

    This feature is only available in Fusion 5.9.5 and later versions of Fusion 5.9.

    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 Lucidworks AI Gateway service when this stage is configured.

    More detailed information to configure this stage is in Configure Lucidworks AI vector search.

    This query stage must be placed before the Solr Query stage.

    Configuration

    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.

    Generate a vector based on the input. Uses a Lucidworks AI embedding model to encode the input to a vector representation. Will be skipped if the input is blank or wildcard (* or *:*).

    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

    Lucidworks AI account name. This entry should match the account name set in the LWAI Gateway.

    modelType - stringrequired

    Lucidworks AI model to use for encoding.

    queryInput - stringrequired

    The query itself is retrieved from here.

    Default: <request.params.q>

    outputContextVariable - stringrequired

    The context variable into which the vector will be placed.

    Default: vector

    useCaseConfig - array[object]

    Default: {"key":"dataType","value":"query"}

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    }    value : {
     display name: Parameter Value
     type: string
    }    }

    modelConfig - array[object]

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    }    value : {
     display name: Parameter Value
     type: string
    }    }

    failOnError - boolean

    Flag to indicate if this stage should throw an exception if an error occurs while generating an encoding.

    Default: false