All - Activity - TQuy - Rasa Community Forum
Forum Posts by TQuy
Cannot terminate rasa action server and rasa run using "Ctrl + c" or "Ctrl + Pause" in command prompt
Whenever I run rasa run actions or rasa run, I cannot terminate it in terminal using keys. I tried to reset my window but it’s still doesn’t work.
How to scale Rasa NLU for production?
So have you solved your problem yet? Is Rasa scalable? I want to run multiple replica of Rasa to handle 100s conversations at the same time.
Bots in production
I want to run multiple instances of Rasa on different servers so that we can handle 100s conversations at the same time. How can I do that?
Action_default_fallback often predicted as next action after correct action was predicted
You can try changing the priority of policies, in which the form policy should be the first one.
Add some fields to events before storing them to tracker stores
I want to add some fields to the events before saving them to the tracker stores such as
{
"sender_id": "user_id", # instead of default id
"timestamp": 1528402837.617099,
"event": "bot",
"text": "what your bot said",
"data": "some data"
}
Is there any way? If yes, can you provide more details?
Set slot using button
I can make it works, but I hate the fact that I have to write my own message instead of pushing button every time I use interactive learning.
In form, I write utter_ask_ with button, but when I use interactive learning, I have to write my own message. Can anyone help?
class ConfirmForm(FormAction):
"""Let the user confirm if the captured entities are correct"""
def name(self) -> Text:
return "confirm_form"
@staticmethod
def require...
Moving to new line when writing response for retrieval actions
Is there any progress with this issue? I think the retrieval function is really useful, especially when dealing with factoid question for custom services.
Newline in Response Phrases (Retrieval action)
I have tried all the methods to move to newline in the response but all failed, could anyone help?
Modelling hierarchical intent structure
I want to classify my intent chitchat into more specific intent such as questions about name, questions about age. Is there any way for me to perform this? I want these intents to be a sub-intent of chitchat since I don’t want the chatbot to identify these intents accidentally.
Rasa stop responding after long time inactive
I run rasa with ngrok and server; it runs fine until I left it inactive for an hour, it stops responding and I have to restart ngrok or server. How can I fix this problem?
Help with deprecated Rasa X Community Edition
You misunderstand me; I am trying to do Handling unhappy paths, according to Forms. I try to use interactive learning but it fails.
Entities are extracted but the slots are not filled
After changing auto_fill: true, the slots are filled, but then action_fallback is called and all the slots are empty again.