Get Serving Config Result
Constructors
Types
Properties
Condition boost specifications. If a product matches multiple conditions in the specifications, boost scores from these specifications are all applied and combined in a non-linear way. Maximum number of specifications is 100. Notice that if both ServingConfig.boost_control_ids and SearchRequest.boost_spec are set, the boost conditions from both places are evaluated. If a search request matches multiple boost conditions, the final boost score is equal to the sum of the boost scores from all matched boost conditions. Can only be set if solution_types is SOLUTION_TYPE_SEARCH.
How much diversity to use in recommendation model results e.g. medium-diversity
or high-diversity
. Currently supported values: * no-diversity
* low-diversity
* medium-diversity
* high-diversity
* auto-diversity
If not specified, we choose default based on recommendation model type. Default value: no-diversity
. Can only be set if solution_types is SOLUTION_TYPE_RECOMMENDATION.
Whether to add additional category filters on the similar-items
model. If not specified, we enable it by default. Allowed values are: * no-category-match
: No additional filtering of original results from the model and the customer's filters. * relaxed-category-match
: Only keep results with categories that match at least one item categories in the PredictRequests's context item. * If customer also sends filters in the PredictRequest, then the results will satisfy both conditions (user given and category match). Can only be set if solution_types is SOLUTION_TYPE_RECOMMENDATION.
Facet specifications for faceted search. If empty, no facets are returned. The ids refer to the ids of Control resources with only the Facet control set. These controls are assumed to be in the same Catalog as the ServingConfig. A maximum of 100 values are allowed. Otherwise, an INVALID_ARGUMENT error is returned. Can only be set if solution_types is SOLUTION_TYPE_SEARCH.
The id of the model in the same Catalog to use at serving time. Currently only RecommendationModels are supported: https://cloud.google.com/retail/recommendations-ai/docs/create-models Can be changed but only to a compatible model (e.g. others-you-may-like CTR to others-you-may-like CVR). Required when solution_types is SOLUTION_TYPE_RECOMMENDATION.
How much price ranking we want in serving results. Price reranking causes product items with a similar recommendation probability to be ordered by price, with the highest-priced items first. This setting could result in a decrease in click-through and conversion rates. Allowed values are: * no-price-reranking
* low-price-reranking
* medium-price-reranking
* high-price-reranking
If not specified, we choose default based on model type. Default value: no-price-reranking
. Can only be set if solution_types is SOLUTION_TYPE_RECOMMENDATION.