# Getting a JSON response instead of a text message

**URL:** <https://forum.rasa.com/t/getting-a-json-response-instead-of-a-text-message/29730>\
**Category:** Getting Started with Rasa\
**Created:** [June 3, 2020, 12:33pm UTC](https://forum.rasa.com/t/getting-a-json-response-instead-of-a-text-message/29730 "2020-06-03T12:33:04Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![brunogcarneiro](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/brunogcarneiro/32/9367_2.png) [@brunogcarneiro](https://forum.rasa.com/u/brunogcarneiro)\
**Post date:** [June 3, 2020, 12:33pm UTC](https://forum.rasa.com/t/getting-a-json-response-instead-of-a-text-message/29730/1 "2020-06-03T12:33:04Z")

</div>

Hello!

\*I am sorry if I am posting it in the wrong place…

I am trying to follow this tutorial ([https://rasa.com/docs/rasa/user-guide/building-assistants/#id8](https://rasa.com/docs/rasa/user-guide/building-assistants/#id8)).

After I execute the command

`rasa shell`

When I send a message to the bot, it replies with a json file instead of a text message.

What can be wrong?

> (rasavenv) Pessoal@bcarneiro rasa-assistant % rasa train /Users/Pessoal/rasavenv/lib/python3.7/site-packages/rasa/core/domain.py:151: FutureWarning: No tracker session configuration was found in the loaded domain. Domains without a session config will automatically receive a session expiration time of 60 minutes in Rasa version 2.0 if not configured otherwise. session\_config = cls.\_get\_session\_config(data.get(SESSION\_CONFIG\_KEY, {})) No stories present. Just a Rasa NLU model will be trained. Training NLU model… 2020-06-03 09:10:20 INFO rasa.nlu.training\_data.training\_data - Training data stats: 2020-06-03 09:10:20 INFO rasa.nlu.training\_data.training\_data - Number of intent examples: 23 (3 distinct intents) 2020-06-03 09:10:20 INFO rasa.nlu.training\_data.training\_data - Found intents: ‘greet’, ‘bye’, ‘thank’ 2020-06-03 09:10:20 INFO rasa.nlu.training\_data.training\_data - Number of response examples: 0 (0 distinct responses) 2020-06-03 09:10:20 INFO rasa.nlu.training\_data.training\_data - Number of entity examples: 0 (0 distinct entities) 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component WhitespaceTokenizer 2020-06-03 09:10:20 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component RegexFeaturizer 2020-06-03 09:10:20 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component LexicalSyntacticFeaturizer 2020-06-03 09:10:20 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component CountVectorsFeaturizer 2020-06-03 09:10:20 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component CountVectorsFeaturizer 2020-06-03 09:10:20 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:20 INFO rasa.nlu.model - Starting to train component DIETClassifier /Users/Pessoal/rasavenv/lib/python3.7/site-packages/rasa/utils/common.py:351: UserWarning: You specified ‘DIET’ to train entities, but no entities are present in the training data. Skip training of entities. Epochs: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:05\<00:00, 17.02it/s, t\_loss=1.058, i\_loss=0.001, i\_acc=1.000] 2020-06-03 09:10:35 INFO rasa.utils.tensorflow.models - Finished training. 2020-06-03 09:10:35 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:35 INFO rasa.nlu.model - Starting to train component EntitySynonymMapper 2020-06-03 09:10:35 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:35 INFO rasa.nlu.model - Starting to train component ResponseSelector 2020-06-03 09:10:35 INFO rasa.nlu.selectors.response\_selector - Retrieval intent parameter was left to its default value. This response selector will be trained on training examples combining all retrieval intents. 2020-06-03 09:10:35 INFO rasa.nlu.model - Finished training component. 2020-06-03 09:10:35 INFO rasa.nlu.model - Successfully saved model into ‘/var/folders/nd/f8y5zkb51c958kr6k1q\_y3v80000gp/T/tmpfyfcth1s/nlu’ NLU model training completed. /Users/Pessoal/rasavenv/lib/python3.7/site-packages/rasa/core/domain.py:151: FutureWarning: No tracker session configuration was found in the loaded domain. Domains without a session config will automatically receive a session expiration time of 60 minutes in Rasa version 2.0 if not configured otherwise. session\_config = cls.\_get\_session\_config(data.get(SESSION\_CONFIG\_KEY, {})) Your Rasa model is trained and saved at ‘/Users/Pessoal/Projects/rasa-assistant/models/nlu-20200603-091035.tar.gz’. (rasavenv) Pessoal@bcarneiro rasa-assistant % rasa shell NLU model loaded. Type a message and press enter to parse it. Next message: bye! { “intent”: { “name”: “bye”, “confidence”: 0.9999997615814209 }, “entities”: , “intent\_ranking”: [{ “name”: “bye”, “confidence”: 0.9999997615814209 }, { “name”: “thank”, “confidence”: 9.6994156706387e-08 }, { “name”: “greet”, “confidence”: 9.375192888683159e-08 }], “response\_selector”: { “default”: { “response”: { “name”: null, “confidence”: 0.0 }, “ranking”: , “full\_retrieval\_intent”: null } }, “text”: “bye!” } Next message:

---

<div class="post-metadata">

**Author:** ![erohmensing](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/erohmensing/32/1789_2.png) [@erohmensing](https://forum.rasa.com/u/erohmensing)\
**Post date:** [June 4, 2020, 9:54am UTC](https://forum.rasa.com/t/getting-a-json-response-instead-of-a-text-message/29730/2 "2020-06-04T09:54:16Z")

</div>

Hi! Looks like you’ve accidentally trained an NLU-only model: `Your Rasa model is trained and saved at ‘/Users/Pessoal/Projects/rasa-assistant/models/nlu-20200603-091035.tar.gz’`

In doing so, when you use `rasa shell` you automatically do `rasa shell nlu` which just parses user messages.

This is why it trained only NLU: No stories present. `Just a Rasa NLU model will be trained.`

Perhaps your stories aren’t in the `data` directory?

---

<div class="post-metadata">

**Author:** ![brunogcarneiro](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/brunogcarneiro/32/9367_2.png) [@brunogcarneiro](https://forum.rasa.com/u/brunogcarneiro)\
**Post date:** [June 4, 2020, 11:49am UTC](https://forum.rasa.com/t/getting-a-json-response-instead-of-a-text-message/29730/3 "2020-06-04T11:49:53Z")

</div>

Thank you @erohmensing!

I have created the file in the root folder instead of the data folder.