# Transformers Extension AI Functions (Release 5.2.0)

**URL:** <https://community.exasol.com/t/transformers-extension-ai-functions-release-5-2-0/307>\
**Category:** Product News\
**Tags:** integration, ai, udf\
**Created:** [September 4, 2026, 1:00pm UTC](https://community.exasol.com/t/transformers-extension-ai-functions-release-5-2-0/307 "2026-09-04T13:00:27Z")\
**Posts on this page:** 2\
**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:** [September 4, 2026, 1:00pm UTC](https://community.exasol.com/t/transformers-extension-ai-functions-release-5-2-0/307/1 "2026-09-04T13:00:27Z")

</div>

We released version **5.2.0** of the Transformers Extension on [Github](https://github.com/exasol/transformers-extension/releases#release-5.2.0) 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**

Since our last announcement, our AI Functions set has been completed. AI\_ANSWER, AI\_CLASSIFY, AI\_SENTIMENT, AI\_TRANSLATE and AI\_EXTRACT\_ENTITIES are now available.  
Additionally, the upload of models to the BucketFS has gotten a rework to allow the use of bigger models.  
We also added a new script which installs all available UDF’s in Database.  
Lastly, the transformers package was updated from version 4 to version 5.

**⚠ BREAKING CHANGES:**

In transformers version 5, the pipeline for question-answering has been removed. For our AI\_ANSWER\_EXTEDNED UDF, we replaced it with the text-generation pipeline. You will not be able to use you old question-answering models with this new implementation, switch to text-generation models instead. Make sure these models support using a chat\_template(instruct models).

(The translation pipeline was also removed, but we decided to maintain it ourselves for  
now, so the AI\_TRANSLATE\_EXTENDED UDF is unaffected.)

---

<div class="post-metadata">

**Author:** ![spareperegrine64](https://avatars.discourse-cdn.com/v4/letter/s/71c47a/32.png) [@spareperegrine64](https://community.exasol.com/u/spareperegrine64)\
**Post date:** [September 16, 2026, 1:32pm UTC](https://community.exasol.com/t/transformers-extension-ai-functions-release-5-2-0/307/2 "2026-09-16T13:32:50Z")

</div>

> [@Marlene\_Kreß](#):
>
> We released version 5.2.0 of the Transformers Extension on Github and Pypi. 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 directly into Exasol’s filesystem BucketFS, and use them on your data using provided UDF’s.

Thanks for the release note, Marlene. The completed AI Functions set is a nice milestone, especially having translate, sentiment, classification and entity extraction usable directly in Exasol without wiring half a zoo around it. The bigger model upload rework also sounds very welcome, BucketFS model handling was usually where reality started throwing chairs. Small heads-up: there’s a typo in “AI\_ANSWER\_EXTEDNED”, unless the function name really contains that spelling. Also good call on calling out the question-answering pipeline change clearly, that one can bite people hard during upgrades.