Rasa_nlu interpreter - how to load latest model?

Hi! I have one question. We use rasa nlu and core together with some custom actions. In the .py file describing the custom functions, we import rasa nlu model with: interpreter = Interpreter.load(“path/to/model”)

the problem is, that after we create a new model, we have to change the model name in the code. Is there a way to load latest model by default automatically? Or can I create a new model under some predefined name?

Thank you in advance, Lena

Hi,

If you target the parent directory of your models, normally it should load the latest version. Could you try this solution ?

You can fixed the model name when you train your model by using the flag --fixed_model_name

Thank you for the suggestion. I have tried it and it doesn’t find the model. I will try the solution with the fixed_model_name, it sounds good!