Product Selector

Fusion 5.9
    Fusion 5.9

    Ray/Seldon Vectorize Query Stage

    Table of Contents

    The Ray/Seldon Vectorize Query stage generates a vector based on the current query string (q parameter). In Managed Fusion 5.9.11 and earlier, this stage is called Seldon Vectorize Query.

    This feature is only available in Managed Fusion 5.9.x for versions 5.9.6+.

    For more information on setting up vector search with Ray or Seldon, see Configure Ray/Seldon 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 current query string (q parameter). Uses a machine learning model to encode the raw query string (q parameter) to a vector representation. Will be skipped if query string is blank or wildcard (* or *:*). Note this will not work well if the incoming q parameter is a Solr query parser string (e.g. field_t:foo) rather than a raw user query string. Note that the Output Context Variable must match the Hybrid Query stage Vector Context Variable.

    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.

    queryInput - stringrequired

    The query itself is retrieved from here. This field supports Template Expressions such as '<request.params.q>' to evaluate the original user query.

    Default: <request.params.q>

    modelInputFieldName - stringrequired

    Name to specify for the input parameter when sending the query string 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

    vectorContextKey - stringrequired

    The key (string) in which to put the resulting vector as a string context variable.

    Default: vector

    failOnError - boolean

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

    Default: false