Hi,
Big fan of Rasa and the direction! I’m trying out rasa x for the first time this weekend. I have it running use the rasa-x helm chart on a digital ocean k8s cluster and have forked the carbon-bot demo app in order to import it to rasa-x using integrated version control. I was able to import carbon-bot successfully, but when I go to train, it seems to fail silently. When I tail the logs for the rasa-x service in kubernetes, I consistently see the below error message pop up when trying to do the training. Is there a sample app that works out of the box with rasa-x as far as training goes? Also, what do you recommend as the workflow for initiating training in rasa-x on either the rasa-demo app (sara) or carbon-bot?
Thanks again for a great project!
Could not complete training request as your training data contains retrieval intents of the form 'intent/response_key'. Please use the CLI to train your model (`rasa train`).
[2020-02-02 20:42:57 +0000] [24] [ERROR] Exception occurred while handling uri: 'http://138.197.54.108/api/projects/default/models/jobs'
Traceback (most recent call last):
File "/usr/local/lib/python3.6/site-packages/sanic/app.py", line 942, in handle_request
response = await response
File "/usr/local/lib/python3.6/site-packages/rasax/community/api/decorators.py", line 177, in decorated_function
return await await_and_return_response(args, kwargs, request)
File "/usr/local/lib/python3.6/site-packages/rasax/community/api/decorators.py", line 107, in await_and_return_response
response = await response
File "/usr/local/lib/python3.6/site-packages/rasax/community/api/blueprints/models.py", line 178, in train_model
content = await stack_service.start_training_process()
File "/usr/local/lib/python3.6/site-packages/rasax/community/services/stack_service.py", line 246, in start_training_process
raise ValueError("Unable to train on data containing retrieval intents.")
ValueError: Unable to train on data containing retrieval intents.