# Custom response selector generated by NLG models

**URL:** <https://forum.rasa.com/t/custom-response-selector-generated-by-nlg-models/57176>\
**Category:** Rasa Open Source\
**Created:** [February 11, 2023, 4:20pm UTC](https://forum.rasa.com/t/custom-response-selector-generated-by-nlg-models/57176 "2023-02-11T16:20:25Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![agokrani](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/agokrani/32/22428_2.png) [@agokrani](https://forum.rasa.com/u/agokrani)\
**Post date:** [February 11, 2023, 4:20pm UTC](https://forum.rasa.com/t/custom-response-selector-generated-by-nlg-models/57176/1 "2023-02-11T16:20:25Z")

</div>

Hello,

I am wondering if there is a way to customize rasa where I can use a language model to handle my utter actions.

For example: if I have action: utter\_cheer\_up for intent mood\_unhappy. Instead of defining a hardcode response, I can give cheer\_up as a prompt to language model to generate a response and handle the utter\_action.

I would really like to implement this functionality by myself in Rasa. If you can give me guidance on what would be the best way to do this. That would be really helpful.

---

_[View the full topic](https://forum.rasa.com/t/custom-response-selector-generated-by-nlg-models/57176)._