All - Activity - Cekir - Rasa Community Forum

Custom list of slots in a form

Hey @desmarchris
Thank you for your answer,

Well, the problem is, that in fact I do not have the full list of variables at the moment of starting Rasa (to be precise, the list of variables may change while Rasa is running). What is more, there will be thousands of variables in the production.

How to inject new data in rasa using api

POST http://localhost:5005/webhooks/rest/webhook
{
  "sender": "Your Sender",
  "message": "Your Message"
}

Multi-users entities/intents/slots management

Rasa manages the multi-user environment by default. Each user has their own Tracker that stores all the data. Having said that, I am not sure where does your problem come from. How do you send the messages to Rasa? If you use RestAPI, you have to provide the user and the message with every message.

Long response time

Have you tried to use the debug mode (–debug parameter)? If you use this, you will be able to see what exactly takes so much time.

Custom list of slots in a form

Hi,
I am trying to create a dynamic form that gets the slots from an external tool. The use case is that the user chooses an item from a catalog, and each item has different list of parameters that needs to be collected. I understand that I need to use the FormValidationAction and override required_...

Running separate core and nlu

Hi, The following video: https://www.youtube.com/watch?v=jMGgT4lgI28 suggests to use 2 NLU servers for single core server. I am assuming then, that they should be run separately. Am I missing something?

Keeping the bot silent

Hi,
I am planning to create a slack bot that answers only when it knows the answer. The bot would keep silent until it detects that the slack message from any user in the channel is a question it can answer to. Tagging the bot is not an option - the channel participants should talk normally, and whe...

An operating question for Rasa's KerasPolicy

Actually, The policy is run both during training and during action prediction. During training, The neural network is trained with the provided stories, and during prediction the neural network transforms the vector of features (intents, slots and previous actions) into the vector of probabilities for the next action.

Different intent confidence depending on unfeaturized entities

I have actually added a custom nlu component that anonymizes the names in the message after the entities are detected but before the featurizer starts, but it does not work. Is this because the features are set in tokens in the tokenizer, and they are just extracted from the tokens in the featurizer.

Formbot - TypeError: utter_message() missing 1 required positional argument: 'text'

Yes, after upgrading Rasa, everything works well. Thank you.

Different intent confidence depending on unfeaturized entities

Hi,
I need to detect contact details of the employees from the database. For detecting the entities I am using lookup tables. The name and surname are unfeaturized:

entities:
  - employee_first_name
  - employee_surname

slots:
  employee_first_name:
    type: unfeaturized
  employee_surname:

Formbot - TypeError: utter_message() missing 1 required positional argument: 'text'

Yes, I was using the master branch. It happened on both 1.6 and 1.4. Interesting. I have just installed Rasa 1.7 on a new environment and it says that templates have been renamed to responses.

Formbot - TypeError: utter_message() missing 1 required positional argument: 'text'

Hi,
I am trying to go through the formbot example. The way it is written does not train at all, as the messages in the domain.yml file are gathered in the "responses" section. Rasa does not understand this section. Am I missing something?
So, I have added the utter actions and changed the "response..."