I have used regexes for my chatbot. The issue I am facing is RASA always responses back with action_default_fallback message

When I checked it in debug mode, Initially it predicted correctly

rasa.core.processor - Received user message 'sys2 bp1' with intent '{'name': 'SYS2_BP1@lkdfk0984', 'confidence': 0.45993921160697937}' and entities '[{'entity': 'sys2_regex', 'start': 0, 'end': 4, 'confidence_entity': 0.9999407529830933, 'value': 'sys2', 'extractor': 'DIETClassifier'}]'

But later

rasa.core.processor - Predicted next action 'action_default_fallback' with confidence 0.30.

I have attached the complete debug message & the pipeline I have used

Thanks in advance

error.txt (8.4 KB) config.yml (1.5 KB)

1 Like

Please remove the ambiguity_threshold from config and train again

I tried removing the ambiguity_threshold from config but I am still getting the same error. I am still facing the same issue.

Hey, what is the “predicted next action” after removing the “ambiguity_threshold”? Also, how much is the confidence?

Hi, I am getting the below

2022-10-12 16:18:58 DEBUG    rasa.core.policies.ensemble  - Predicted next action using RulePolicy.
2022-10-12 16:18:58 DEBUG    rasa.core.processor  - Predicted next action 'action_default_fallback' with confidence 0.30.

I have also attached the complete debug notes

Debug.txt (13.6 KB)

Hi, can you provide your current nlu, stories, rules and config file?

This question has already been answered in other posts. Below is my proposed solution:

This error is usually caused when there are not enough stories for rasa to learn what action to perform next. I also ran into this problem, and apart from adding more stories, what really solved it was to explicitly state in the rules that the bot should execute the action_listen after the action in which it was receiving the fallback. In my house I only had the fallback with a single action, so I only added it once. If it happens to you with many actions, this may not be the most elegant option, but it is functional.


IMPORTANT! Remember that if in the rules you indicate that the action_listen must be executed after an action, you must also add it in all the stories that after this action an intent is executed, so that the action_listen can be executed, this way the rule is not contradicted.


Another possible solution would be to add stories in which after the action that launches the Fallback, a user intent appears, so that Rasa would learn that after that action it must wait for a response from the user.

1 Like

Hi, I am sharing some of the files I have in the training model

sys3_nlu.yml (39.1 KB) domain_sys3.yml (53.8 KB) sys3_stories.yml (8.3 KB) sys2_nlu.yml (44.1 KB) sys2_stories.yml (8.8 KB) domain_sys2.yml (37.4 KB) rules.yml (347 Bytes)

In my case I am getting action_default_fallback for many intents & also the different data (intents) that RASA has to process are very similar.

have you solved this problem? facing the same issue