# Remove semantic duplicates in retrieval

**URL:** <https://discuss.elastic.co/t/remove-semantic-duplicates-in-retrieval/385456>\
**Category:** Elasticsearch\
**Created:** [March 15, 2026, 5:30pm UTC](https://discuss.elastic.co/t/remove-semantic-duplicates-in-retrieval/385456 "2026-03-15T17:30:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![alexander.korkhov](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/alexander.korkhov/32/133918_2.png) [@alexander.korkhov](https://discuss.elastic.co/u/alexander.korkhov)\
**Post date:** [March 15, 2026, 5:30pm UTC](https://discuss.elastic.co/t/remove-semantic-duplicates-in-retrieval/385456/1 "2026-03-15T17:30:22Z")

</div>

ElasticSeach indexes poster events retrieved from different sources. The same event (for example, a performance) can be retrieved from different sources. Is it possible to somehow organize the data retrieval so that only one such event is returned without duplicates? Use the source as the priority. The names may not exactly match.