# ELSER for long texts

**URL:** <https://discuss.elastic.co/t/elser-for-long-texts/370928>\
**Category:** Elasticsearch\
**Created:** [November 22, 2024, 6:59am UTC](https://discuss.elastic.co/t/elser-for-long-texts/370928 "2024-11-22T06:59:57Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sarah2](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/sarah2/32/137582_2.png) [@Sarah2](https://discuss.elastic.co/u/Sarah2)\
**Post date:** [November 22, 2024, 6:59am UTC](https://discuss.elastic.co/t/elser-for-long-texts/370928/1 "2024-11-22T06:59:57Z")

</div>

I am using Elastic Search 8.11 and want to use ELSER to incorporate semantic search. But fields I have to perform search is long text fields.

I found this [link](https://www.elastic.co/guide/en/machine-learning/8.11/ml-nlp-limitations.html) saying

> If your data set contains long documents, divide them into smaller segments before ingestion if you need the full text to be searchable.

But I am not able to figure out and find reference that how exactly that is supposed to be done.

Can someone share more details on this?