Promoting diversity among items in a search result has been shown to increase user satisfaction, compared to relevancy only based ranking. In this talk, we'll present how we went about implementing search result diversification methods across different vertical search engines. Starting from zero with no diversification at all, exploring simple heuristic-based methods and moving onwards to more complex ones based on entropy and determinantal point processing. We'll also discuss evaluation methods and useful tooling around that. Presented by Dmitry Kan, Principal AI Scientist at Silo AI and Daniel Wärnå, AI Engineer, Silo AI. YouTube recording: https://www.youtube.com/watch?v=bri0C28mfl8 Code demoed: https://github.com/DmitryKey/bert-solr-search/tree/master/src/diversify