Rasa.core.agent - Could not load model due to Error initializing graph component for node run_DIETClassifier

Rasa Open Source Feedback on Rasa Open Source
1

I got the following error, when I switch to use bert-base-chinese: rasa.core.agent - Could not load model due to Error initializing graph component for node run_DIETClassifier

pipeline:

  • name: JiebaTokenizer
  • name: RegexFeaturizer
  • name: LanguageModelFeaturizer model_name: “bert” model_weights: “bert-base-chinese”
  • name: DIETClassifier
    epochs: 300
    constrain_similarities: True
  • name: FallbackClassifier threshold: 0.8 ambiguity_threshold: 0.1

Rasa Version : 3.5.11 Minimum Compatible Version: 3.5.0 Rasa SDK Version : 3.5.1 Python Version : 3.10.9 Operating System : Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 Python Path : /home/anaconda3/bin/python

2

Hello, The error message you received, “Could not load model due to Error initializing graph component for node run_DIETClassifier,” indicates a problem with initializing the DIETClassifier component in your Rasa pipeline when using the “bert-base-chinese” language model.

This error typically occurs when there is an incompatibility between the Rasa version, Rasa SDK version, and the installed dependencies. In this case, it’s possible that the version of Rasa or the Rasa SDK you are using is not compatible with the “bert-base-chinese” model. To resolve this issue, you can try the following steps:

Update Rasa and Rasa SDK to their latest compatible versions. Make sure all the necessary dependencies for the “bert-base-chinese” model are installed correctly. Double-check that the model weights for the “bert-base-chinese” model are accessible and properly configured in your Rasa project.

I hope the information helps you.