# Release of version 3.0.0 of the Transformers Extension

**URL:** <https://community.exasol.com/t/release-of-version-3-0-0-of-the-transformers-extension/250>\
**Category:** Product News\
**Tags:** integration, ai, udf\
**Created:** [November 7, 2025, 11:14am UTC](https://community.exasol.com/t/release-of-version-3-0-0-of-the-transformers-extension/250 "2025-11-07T11:14:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Marlene\_Kreß](https://avatars.discourse-cdn.com/v4/letter/m/ecb155/32.png) [@Marlene\_Kreß](https://community.exasol.com/u/Marlene_Kre%C3%9F)\
**Post date:** [November 7, 2025, 11:14am UTC](https://community.exasol.com/t/release-of-version-3-0-0-of-the-transformers-extension/250/1 "2025-11-07T11:14:01Z")

</div>

We released version **3.0.0** of the **Transformers Extension** on [Github](https://github.com/exasol/transformers-extension/releases/tag/3.0.0) and [Pypi](https://pypi.org/project/exasol-transformers-extension/).  
The Exasol Transformers Extension allows you to use pre-trained machine learning models from 🤗 Hugging Face directly in your Exasol instance.  
It lets you install the models via the [transformers-api](https://github.com/huggingface/transformers) directly into Exasol’s filesystem [BucketFS](https://docs.exasol.com/db/latest/database_concepts/bucketfs/bucketfs.htm), and use them on your data using provided UDF’s.

📝 **Summary**

In this release, we added a `return_ranks` and a `rank` column to some UDF’s, to improve the flexibility in building Pipelines using the Exasol Transformers Extension.  
There are some dependency updates and internal changes as well, please refer to the [changelog](https://github.com/exasol/transformers-extension/releases/tag/3.0.0) if you are interested.

⚠ **BREAKING CHANGES** :

- The Sequence-Classification UDF’s (single-text and text-pair) now require a `return_ranks` input Column, which is used to determine how many results per input should be returned.

- The Sequence-Classification UDF’s (single-text and text-pair) now return a `rank` column with the rank of the results.

- The Zero-Shot-Classification UDF now requires a `return_ranks` input Column, which is used to determine how many results per input should be returned.

Please refer to the [user guide](https://github.com/exasol/transformers-extension/blob/user_guide/user_guide.md) for Details on how to use these UDF’s going forward.