Fusion AI

Version 4.1
How To
Documentation
    Learn More

      Recommend Items for Item Stage

      Table of Contents

      The Recommend Items for Item query pipeline stage uses signals about users' item choices to recommend related items based on a specific item. Relationships between items can be based on different criteria, such as click patterns, people who bought this also bought that, percentage match of document tags, and so on.

      Given an item ID, this stage performs a secondary query to the _items_for_item_recommendations collection to find related items, then retrieves those items from the main collection.

      This pipeline stage uses items-for-item recommendations that have been precomputed by an ALS Recommender.

      See also Items-for-item Recommendations to learn how to configure this recommender type and fetch recommendations.

      Prerequisites

      Enable recommendations:

      Before creating a Recommend Items for Item stage, enable recommendations.

      • Fusion UI – In Collections Manager, click the settings icon next to the collection > Enable Recommendations.

      • Using the REST API – Use this command to enable recommendations:

        curl -u admin:<password> -X PUT \http://<hostname>:<port>/api/v1/collections/<collection-name>/features/recommendations -H 'content-type: application/json' -d '{"enabled":true}
      When you enable recommendations, Fusion creates a query pipeline that already contains this stage, and that is configured for boosting. The query pipeline is <collection>_items_for_item_recommendations.

      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.

      When using Fusion's REST API, the ID for this stage is:item-recommendation.

      Loading liquid template...

      Loading configuration schema...