What is the best Rasa version to use for using bert models in the pipeline? Since I check the Rasa github repo and others project and it seems there are some components are deprecated and some codes are changed.

Hi, can you specify what’s deprecated? If you can point us to something that seems out of date or stale, that would be very helpful, then we can make sure we update it! You can use any of the more recent Rasa versions (1.8 and above, though I would strongly recommend using more recent versions). The difference is that before 2.1 you had to use: - HFTransformersNLP - LanguageModelTokenizer - LanguageModelFeaturizer If you use 2.1 or above, LanguageModelTokenizer and HFTransformersNLP are deprecated. Instead, you should use just any Tokenizer (for example, WhitespaceTokenizer) paired with LanguageModelFeaturizer in the pipeline: - WhitespaceTokenizer - LanguageModelFeaturizer Does that make sense? Note that there is a slight increase in inference time for the LanguageModelFeaturizer component in versions 2.8.9 and above: this is related to the TensorFlow upgrade.

Ah I see, well I’m glad we could get you sorted! :slight_smile:

Rasa Version with Transformer

Rasa Open Source

Pain (Pain) November 24, 2021, 6:37am 3

Thanks for this great answer, it is very useful. By deprecated I mean HFTransformersNLP & LanguageModelTokenizer components.

Topic		Replies	Views
Pipiline for BERT Rasa Open Source	1	362	May 17, 2021
Support for Language Models inside Rasa Release Announcements community , rasa	25	13061	November 25, 2021
Correct tokenizer for BERT Rasa/LaBSE Rasa Open Source	2	304	January 17, 2025
KeyError: 'HFTransformersNLP' Rasa Open Source	1	430	November 22, 2021
How to add my own trained BERT + Tensorflow model to RASA Rasa Open Source	2	752	November 20, 2020

Rasa Version with Transformer

Related topics