It is recommended to try using model_confidence=linear_norm to make it easier to tune fallback thresholds. Users/mo/.envrasa/lib/python3.8/site-packages/rasa/utils/train_utils.py:531: UserWarning: model_confidence is set to softmax.
It will be set to True by default, Rasa Open Source 3.0.0 onwards. It is recommended to set it to True when using cross-entropy loss. Users/mo/Rasa/.envrasa/lib/python3.8/site-packages/rasa/utils/train_utils.py:558: UserWarning: constrain_similarities is set to False. Please update your configuration file to use loss_type=cross_entropy instead. Users/mo/Rasa/.envrasa/lib/python3.8/site-packages/rasa/utils/train_utils.py:96: FutureWarning: loss_type=softmax is deprecated. 19:13:02 INFO rasa.model - Loading model models/… Maybe someone in the community have an idea what the problem is. Right know it is very much a FAQ bot.īut I am struggling with some errors that I can’t find my way around.
Building a bot that started to have some different NLU files.
