Errors when migrating from Dialogflow to Rasa

Hi. I just tried migrating from Dialogflow to Rasa. I’m relatively new to Rasa. I followed the instructions. I’ve placed the dialogflow exported agent folder in the empty rasa/data folder. One thing I noted is that while the intents and entities are exported in the dialoglfow zip file the fulfilment code doesn’t seem to be exported.

The errors i’m getting when I run rasa train nlu:

rasa.nlu.training_data.formats.dialogflow - No training examples found for dialogflow file data\chads\intents\Default Fallback Intent.json!

And the above happens with each of the intents ie there are no training examples.

  • Training data stats: - intent examples: 0 (0 distinct intents) - Found intents: - entity examples: 0 (0 distinct entities) - found entities:

When I run rasa shell nlu the error output is:

rasa.nlu.classifiers.embedding_intent_classifier - Failed to load nlu model. Maybe path C:\Users\jxxxxx\AppData\Local\Temp\tmpylw2bdth\nlu doesn’t exist NLU model loaded. Type a message and press enter to parse it. Next message: Hello 2019-09-24 11:03:05 ERROR rasa.nlu.featurizers.count_vectors_featurizer - There is no trained CountVectorizer: component is either not trained or didn’t receive enough training data 2019-09-24 11:03:05 ERROR rasa.nlu.classifiers.embedding_intent_classifier - There is no trained tf.session: component is either not trained or didn’t receive enough training data { “intent”: { “name”: null, “confidence”: 0.0 }, “entities”: [], “intent_ranking”: [], “text”: “yes” } Next message:

Advice would be great.


hi @Jmg007 - there is no support for migrating the fulfillment code, but it should be relatively straightforward to port them to custom actions Actions

regarding the NLU model not training, that sounds like a bug. Could you please upload a minimal example (doesn’t have to be all your training data) and create an issue?