# How to deploy multiple Deploy RASA\_NLU model

**URL:** <https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872>\
**Category:** \[Deprecated\] Rasa X Community Edition\
**Created:** [August 27, 2019, 11:48am UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872 "2019-08-27T11:48:33Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![Pavan\_gali](https://avatars.discourse-cdn.com/v4/letter/p/71c47a/32.png) [@Pavan\_gali](https://forum.rasa.com/u/Pavan_gali)\
**Post date:** [August 27, 2019, 11:48am UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/1 "2019-08-27T11:48:33Z")

</div>

How to Deploy multiple models in single pipeline.

---

<div class="post-metadata">

**Author:** ![erohmensing](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/erohmensing/32/1789_2.png) [@erohmensing](https://forum.rasa.com/u/erohmensing)\
**Post date:** [August 27, 2019, 2:49pm UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/2 "2019-08-27T14:49:39Z")

</div>

Hi there @Pavan_gali, we don’t currently support multiple NLU models in rasa 1.0 but it is a feature we are considering bringing back. you can see the full discussion here: [Removing projects for Rasa NLU server](http://forum.rasa.com/t/removing-projects-for-rasa-nlu-server/8962)

---

<div class="post-metadata">

**Author:** ![JulianGerhard](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/juliangerhard/32/3781_2.png) [@JulianGerhard](https://forum.rasa.com/u/JulianGerhard)\
**Post date:** [August 28, 2019, 5:03am UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/3 "2019-08-28T05:03:32Z")

</div>

Hi @Pavan_gali

just to make sure: Do you mean using several models, trained with the `rasa train` command for one single bot, or do you mean to e.g. use several `SpacyNLP pipeline` elements, loading different models?

Regards Julian

---

<div class="post-metadata">

**Author:** ![Pavan\_gali](https://avatars.discourse-cdn.com/v4/letter/p/71c47a/32.png) [@Pavan\_gali](https://forum.rasa.com/u/Pavan_gali)\
**Post date:** [August 28, 2019, 7:08am UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/4 "2019-08-28T07:08:38Z")

</div>

we want to load multiple pipelines for different models. config1.yml for model 1 config2.yml for model 2

Now while starting the Rasa server how do i support this. as Rasa takes only one config file(.yml).

---

<div class="post-metadata">

**Author:** ![erohmensing](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/erohmensing/32/1789_2.png) [@erohmensing](https://forum.rasa.com/u/erohmensing)\
**Post date:** [August 28, 2019, 4:14pm UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/5 "2019-08-28T16:14:27Z")

</div>

The config should be part of the model packaging itself, though. How are you using multiple models @Pavan_gali?

---

<div class="post-metadata">

**Author:** ![eashan\_27](https://avatars.discourse-cdn.com/v4/letter/e/c67d28/32.png) [@eashan\_27](https://forum.rasa.com/u/eashan_27)\
**Post date:** [October 11, 2020, 4:53pm UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/6 "2020-10-11T16:53:38Z")

</div>

Hey @erohmensing i have one query regarding the RASA NLU model.When we pass rasa shell nlu on the cmd it returns a JSON as an output of all the intents,entites. So i wanted to ask is there a way we can get that same JSON output when we run our NLU model on RASA X local server?Kindly answer this query it’ll be really helpful

---

<div class="post-metadata">

**Author:** ![mloubser](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mloubser/32/13021_2.png) [@mloubser](https://forum.rasa.com/u/mloubser)\
**Post date:** [October 13, 2020, 7:55am UTC](https://forum.rasa.com/t/how-to-deploy-multiple-deploy-rasa-nlu-model/14872/7 "2020-10-13T07:55:42Z")

</div>

@eashan_27, yes, you can get NLU parsing info back from Rasa X using the [parse message endpoint](https://rasa.com/docs/rasa/pages/http-api#operation/parseModelMessage)
