Over the last year and a half, Wikimedia has switched from a home-grown search solution based on Lucene 2 to a highly redundant Elasticsearch cluster powering billions of user prefix and full-text searches. This talk will outline the brief history of search at Wikimedia, why we went with Elasticsearch, how we've scaled it and what we've built, and finally touch on the integration and features we've provided to users of our platform.
Presented by Nik Everett & Chad Horohoe, Wikimedia