Likes - Activity - tonysinghmss - Rasa Community Forum

Hello @yahiaouik, You can get the sender by using this line of code: sender = tracker.sender_id

@pnandhini Not sure if you’re still having trouble with this, but this is the first result from google when you enter how much data augmentation should I use rasa. I’ll try to do my best, as I’m just entering the ML field, but from what I understand: By default, Rasa will use a common tactic in th…

I am trying to figure out what exactly is data Augmentation and how it works. I read the documentation and tried using augmentation_factor as 20 ( which is default ) and also as 0. Documentation says " You actually want to teach your policy to ignore the dialogue history when it isn’t relevant …

Are you using custom actions or the HTTP API? In case of the HTTPI API: Add a restart event as first item to your event list, and then append all the old events of your trackers and send this of events to HTTP API In case of custom actions: return [Restarted()] + tracker.events

I meant return [UserUtteranceReverted(), ActionReverted()]

try return [FollowupAction(tracker.active_form[‘name’])]. That should take you back to your active form and reask the last question you were asking.

MappingPolicy can be used when prediction is independent of context: Policies

Use MappingPolicy, when you're 100% sure, that you're okay with the exact same reaction every time to a certain intent. I only use it for things like unhappy path in forms. (In a FormAction) Bot: What is your ID? User: I dont want to answer that Bot: Do you want to stop the form? Buttons Yes/No

Hi @sociopath00, @suryavamsi62, please have a look at the docs on adding metadata information to user messages: Custom Connectors. I hope that helps!

I found a tricky way to start another story. The main idea is… Rasa core will continue story if I can make the list of Tracker’s events that are same as when the user started. This is easily possible by returning action_listen and the first user intent of the story sequentially. action.py example …

provide an example(code snippet) for Handing off to a human

It would be great if Clarification will be implemented in Demo Bot. If confidence difference of 2 top intent is very small then it should ask for clarification using Intent Name of Predefined text for each intent. May be put 2 buttons, one for each intent. Also I would like to see Form Action used …

I’d like to see a demo where the bot can save (transcription) of conversation per user.

I’d like the new bot explain how to effectively use trackers

That was an easy fix actually. I needed to use logging.getLogger(name) instead.

Oook sorry for the question before, but after reading the policy, I noticed this : Args: nlu_threshold: minimum threshold for NLU confidence. If intent prediction confidence is lower than this, predict fallback action with confidence 1.0. core_threshold: if NLU confid…

if you pass the payload like this /intent_name, the intent should be picked up automatically

@akelad I did the same. It would be helpful if you guys can add “custom payload” support by default in UserMessage. I was found few examples in http api docs on how to use Buttons, elements, attachments etc. I think it would be a great help for beginners if you can add few examples of each use case…

There is a simple way to build an FAQ with the Rasa Addons package with just one story and one action, avoiding to retrain when questions are added or changed You create an intent substitution rule like this: intent_substitutions:

Hi, I wanted to know if there is any way to register the name of people involved in the conversation in the Rasa X Community version.

You’ll need to do the following:

Write NLU training data to detect intent and entities Add a slot with the same name as the entity (in your case, name) Define a story where the user entering their name is followed by an utter_greet or something Define utter_greet in the domain file to be a template.