[SOLR-16667] LTR Add feature vector caching for ranking

• Type: Improvement
• Status: Open
• Priority: Minor
• Resolution: Unresolved
• Affects Version/s: 9.1.1
• Component/s: contrib - LTR
• Assignee: Unassigned
• Reporter: Anna
• Created: 17/Feb/23 10:44
• Updated: 23/Feb/23 18:30

Description

Currently, the feature vector cache is used only for logging purposes in the learning-to-rank model.

It would be useful to integrate the cache usage also in the ranking phase to speed up the process.