# Running XGBoost Re-Rank Models in Elasticsearch Ingest Pipelines

**URL:** https://discuss.elastic.co/t/running-xgboost-re-rank-models-in-elasticsearch-ingest-pipelines/383054
**Category:** Elasticsearch
**Created:** [October 28, 2025, 5:59pm UTC](https://discuss.elastic.co/t/running-xgboost-re-rank-models-in-elasticsearch-ingest-pipelines/383054 "2025-10-28T17:59:11Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![Shell\_Dias](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/shell_dias/32/136785_2.png) [@Shell\_Dias](https://discuss.elastic.co/u/Shell_Dias)
#### Post date: [October 28, 2025, 5:59pm UTC](https://discuss.elastic.co/t/running-xgboost-re-rank-models-in-elasticsearch-ingest-pipelines/383054/1 "2025-10-28T17:59:11Z")

</div>

How can I run **re-ranking models** within **ingest pipelines** to create a custom field containing the classification result?

For example:  
I have an **XGBoost** model that uses the `predict` method. I’d like to apply it to each document during ingestion so that the prediction result is stored in a new field.

Is it possible to achieve this within an Elasticsearch ingest pipeline?