Superheroes

This is a group for all Rasa Superheroes!

Extract datetime with CALM

Date: Mar 18, 2025
User: souvikg10
@mnchs12312321 - you can use duckling in custom actions instead. use the collect step to retrieve the value and then parse it in a validate_slot_name method to return the slot value which is parsed by duckling.

Command Generation based on NLU prediction

Date: Dec 4, 2024
User: souvikg10
Which LLM are you using? you can also simply map certain slots onto entities if that performs well using slot_mappings and add in your entity extractor in the pipeline prior to the LLMCommandGenerator . there is a component called NLUCommandAdapter which can take the entities extracted from your NL…

Command Generation based on NLU prediction

Date: Dec 3, 2024
User: souvikg10
What would be the difference in comparison to how the command generator works? You can add few shot examples of your intents similar to flows in the flow description to improve the prediction of StartFlow command and add a description in the collect step to improve slot predictions. I think you can…

RASA Pro - Special plans for agencies?

Date: Nov 4, 2024
User: souvikg10
Hey @God_el, Glad to have you back and try out Rasa CALM. There is a free developer license that lets you try out CALM or build with CALM locally - link and you can then request an extended server license up to certain number of convers…

Training with Enterprise Policy and testing with rasa shell always predicts action_listen

Date: May 9, 2024
User: souvikg10
You are missing the flow policy in your config? How are you triggering RAG? possibly using a pattern_search correct? for this you will also need to include the Flow policy as well.

Training with Enterprise Policy and testing with rasa shell always predicts action_listen

Date: May 5, 2024
User: souvikg10
Hi @vishnupriyavr. Could you share your config.yml.

Loading FastText and other language models

Date: Apr 23, 2024
User: souvikg10
The blog I wrote was about 6 years old, I am pretty sure it is now outdated with the newer rasa versions. Any particular reason you want to try fast text vectors?

Rasa PRO 3.8 OPENAI Errors

Date: Apr 23, 2024
User: souvikg10
I believe we are using the Completion API instead of ChatCompletion which unfortunately is not supported in some newer version of gpt-3.5-turbo. We are working towards fixing that. If you are facing this in gpt-4. could you post the full error logs and also the version of openai do you have a spe…

How do I get Rasa to check for available dates for a doctor’s appointment

Date: Feb 18, 2024
User: souvikg10
Try this instead: rasa run actions --actions C:\Users\WORK\Desktop\chatbot\actions\

Notification message

Date: Feb 14, 2024
User: souvikg10
you will need to create an action server, and in a custom action, you can then connect to the graph API.

Seeking Guidance to Improve “buscar_producto” Intent

Date: Nov 14, 2023
User: souvikg10
@Daniel45450 - any reason why you believe this intent is not performing good enough? have you run validations using rasa test nlu with a validation dataset? Look for metric based assessment instead such as F1 scores this should help you pinpointing performances of several intents in your training d…

Rasa Open Source 3.6 launched :rocket:

Date: Jun 28, 2023
User: souvikg10
Hi, The above error is a bug we are addressing right now. It however does not impact the run of the action server.