Release of version 3.0.0 of the Transformers Extension

Product News
, ,
1

We released version 3.0.0 of the Transformers Extension on Github and Pypi.
The Exasol Transformers Extension allows you to use pre-trained machine learning models from :hugs: 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.

:memo: 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 if you are interested.

:warning: 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 for Details on how to use these UDF’s going forward.

2 Likes