I have create a docker image using latest code of RASA nlu and RASA core from github.
I have created a model using docker images of RASA nlu using below command
python -m rasa_nlu.train
–project current --verbose
Using the above trained model I am trying to run RASA core server with below command
docker run -it -p 5005:5005 --mount type=bind,source=/home/docker/rasaproject/models/dialogue,target=/app/dialogue
while server startup I am getting below error
rasa_nlu.model.UnsupportedModelError: The model version is to old to be loaded by this Rasa NLU instance. Either retrain the model, or run withan older version. Model version: 0.0.0 Instance version: 0.15.0a4
I am stuck and any help would be highly appreciated.
Hi, I am also getting the same issue :
rasa.nlu.model.UnsupportedModelError: The model version is to old to be loaded by this Rasa NLU instance. Either retrain the model, or run withan older version. Model version: 0.0.0 Instance version: 0.15.0a6
Any idea, how to resolve it?
Model version: 0.0.0 usually indicates that you are not pointing to a valid trained NLU model. How do you load the NLU model on the server?
I have a problem too, I have trained the model using Docker desktop and the output was .tar.gz
And I was trying to test the model and load the interpreter but it didn’t go well. I was trying to load model and test one data using this code but then the error appears.
interpreter = Interpreter.load(‘C:\Users\Alvi\rasa_testing\models\nlu’)
print(interpreter.parse(“Asus Zenfone Max Pro m2 ram 4 rom 32”))
The model version is to old to be loaded by this Rasa NLU instance. Either retrain the model, or run withan older version. Model version: 0.0.0 Instance version: 0.14.6
Anyone know how to solve this problem?
Hi @alvipranandha. Did you manage to resolve the “model version is too old” issue? Having the same issue and struggling to figure out how to load the model. Especially cause it says version 0.0.0…
@baselsm are you able to use the
Train button to retrain your model?