All - Activity - ruiconti - Rasa Community Forum

Now Available: Integrated Version Control for Rasa X

Hey @tiziano, please make sure all these items are covered:

How to initiate conversation from Rasa first?

Is this error preventing you from running (or training) models? In any case, you can force TensorFlow to not use GPU by setting an environment variable (that must be accessible from all of Rasa’s container instances):
CUDA_VISIBLE_DEVICES=-1

Hey @bhaskar1986, that is a common “issue” and it is very straightforward. As a general rule, every conversation must be initiated from the user as it is standard good practice (and in many cases a compliance constraint) in bot development in order to maintain bots that are triggered and do not respond to unsolicited messages.

Just passing by to share a (perhaps) useful advice. When adding your repository to Rasa X, on Step 2, there is an important step that’s missing in the docs. That is, when you paste your private key, you need to replace new lines with the '\n' character as that’s needed to successfully parse the key from J…

Intent and Entity Design - Organization Dilemma

Hey @Egalite123, I was facing a similar challenge recently. I needed to give the NLU the capacity to recognize similar yet hierarchical intents classification. Intents like “SavingsAccountInterestRate” and “SavingsAccountHowToApply” might share a few words and context.

I’m not sure if I understood what you meant by “generic utter with a variable and change it with the value of the slot according to the intent”. Can you please elaborate and give a few examples?

Hey @Vinicivs, Deu pra entender de onde você vem. Nesse caso, eu acredito que se familiarizar com Python realmente é uma boa...

Nested Intent Classification

Hey @samarth12! It’s strange how I’ve had the same idea a few days back when thinking about a problem here. I’m planning on using three entities to categorize a technical issue.

Hey there! I’m Rui from Brazil. I’m leading a small and beginning team implementing Rasa on a bank. Its main goal is to help: now tech support automating tasks and handling problem support and routing; and later, as a more mature solution, to provide support for customers.

Swamy, this is a common problem in NLP. Rasa tackles this subject by outsourcing methods on entity extraction. Your entity is name and spaCy would be helpful in this case, specifically, providing PERSON entity classification to your NLU pipeline.

@Vinicivs eu recomendaria a documentação oficial que agora tá bem mais completa do que a algum tempo atrás.

How to reset Slots in between the conversation?

Hey Eli, what you want to do is reset the slots, which is something Tracker is responsible for. I like to think that the Tracker object is a watcher on an exchange of Event s between the user and the bot (here as Agent).

Hey there! I’m implementing the usage of an external tracker using the RedisTrackerStore class. I’m aiming to share tracker memory resources between applications.

After updating from 0.10.4 to 0.13.3, I’m having a few issues concerning Tracker.

It seems you’re at the beginning of your project and don’t have enough data. A good tool you can use is Chatito to generate synthetic datasets for any given intent.