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 COLLECTION_NAME_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 the BPR 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.
  • Managed 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 USERNAME:PASSWORD -X PUT http://EXAMPLE_COMPANY.lucidworks.cloud/api/v1/collections/COLLECTION_NAME/features/recommendations -H 'content-type: application/json' -d '{"enabled":true}'
Replace EXAMPLE_COMPANY with the name provided by your Lucidworks representative.
When you enable recommendations, Managed Fusion creates a query pipeline that already contains this stage, and that is configured for boosting. The query pipeline is COLLECTION_NAME_items_for_item_recommendations.

​
Using live signals

The Estimate Recent Results option uses live signals to augment items-for-user recommendations with real-time recommendations. When this is enabled, Managed Fusion first looks up items (from previously-generated recommendations) that are similar to the new items. If there are none then it looks up similar users (who also interacted with that item) to get a list of recommendations based on the new items. It then combines those new recommendations with the job-based recommendations already generated for that user (if any), to generate a final list of 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.