# Run rasa server directly, not from a source environment?

**URL:** <https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284>\
**Category:** Rasa Open Source\
**Created:** [August 29, 2021, 4:07pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284 "2021-08-29T16:07:12Z")\
**Posts on this page:** 20\
**Page:** 1

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 4:07pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/1 "2021-08-29T16:07:12Z")

</div>

I have successfully installed and run the rasa server (Debian/AWS) while within an environment by running:

```
source ./venv/bin/activate
cd ~/htdocs/<my folder for model>
rasa run -m models --enable-api --cors "*"

```

But the server quits whenever I close the terminal.

I suspect it has something to do with running in within the environment, rather than directly.

How do I get it to run directly, or if that’s not the problem, how do I get the server to keep running when the terminal closes?

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 6:03pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/2 "2021-08-29T18:03:49Z")

</div>

@bferster you can create the docker compose environment.

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 6:14pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/3 "2021-08-29T18:14:20Z")

</div>

is that persistent?

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 6:29pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/4 "2021-08-29T18:29:28Z")

</div>

@bferster yes, I think so. It is container based, till you update or trained the model again.

**For example:** I have my Wordpress website running 24x7 on docker based environment, and even my rasa open source, without any terminal open, if you are using Windows or Mac you can easily manage whilst using Docker Desktop, to start or stop containers.

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 6:31pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/5 "2021-08-29T18:31:07Z")

</div>

is there any way to make the source environment I’m using now persistent?

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 6:32pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/6 "2021-08-29T18:32:44Z")

</div>

@bferster for that you need to create the conda environment on server as server run 24x7 so as your chatbot then or may be GitHub actions can help you, I not personally implemented but you can explore.

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 6:35pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/7 "2021-08-29T18:35:17Z")

</div>

@bferster what is you current use case and resources you had for your deployment and for chatbot?

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 29, 2021, 6:36pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/8 "2021-08-29T18:36:44Z")

</div>

Keep in mind that a [Helm Chart Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/helm-chart) or a [Docker Compose Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/docker-compose) is better at handling multiple users than running `rasa run` which is supposed to be used for [Local Mode](https://rasa.com/docs/rasa-x/installation-and-setup/install/local-mode) only.

To quickly test deployment, you can use the [Quick Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/quick-install-script) which is a quick way to do a Helm Chart Installation with a single command.

To understand how deployment works in detail, you can look at the [Rasa Advanced Deployment Workshop](https://www.udemy.com/course/rasa-advanced-deployment-workshop/). It explains how to deploy and manage a Helm Chart Installation, the architecture and role of each pod/container, etc.

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 6:43pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/9 "2021-08-29T18:43:13Z")

</div>

It’s not really a chat bot. I’m working for a university to develop a teacher-training tool where teachers can simulate the classroom environment: [www.lizasim.com](http://www.lizasim.com)

They talk to rasa, and we come up with appropriate responses, based on the intents and entities returned

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 6:45pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/10 "2021-08-29T18:45:25Z")

</div>

I’ve never worked with Python before. Other than Helm, Docker, or Conda, there’s no way I can’t just evecute the server directly, and it will stay up?

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 7:02pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/11 "2021-08-29T19:02:56Z")

</div>

@bferster your use case is very interesting, it means you want to provide teacher a live classroom environment with different sets of questions (asked by students) but how teachers reply or it will be vice-versa, are you able to create this use case or its just a starting/planning?

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 7:08pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/12 "2021-08-29T19:08:05Z")

</div>

We have a training set of 43,000 pairs of teacher-student interactions that have been coded to 34 intents that reflect different ways to teach kids. The teachers are real people, and the students are avatars

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 7:11pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/13 "2021-08-29T19:11:00Z")

</div>

@bferster Teacher provides the input (Real Person) and student will replied (Avatar) Right based on training dataset. Correct?

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 7:15pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/14 "2021-08-29T19:15:07Z")

</div>

Yes. One of the responses is chosen based on the intent found in the live teacher’s remark, with the help of some contextual information. I can’t believe there isn’t a simpler way to get the server persistent than having to learn yet another technology!

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 7:21pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/15 "2021-08-29T19:21:47Z")

</div>

@bferster can you reply few question of mine if you can.

1. What is your website platform Wix, Wordpress etc?
2. What is your front end for chatbot?
3. What is your server machine?

Thanks.

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 29, 2021, 7:22pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/16 "2021-08-29T19:22:40Z")

</div>

Sorry Mr Ferster, you will either need to deploy on a server using [the above methods](http://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/8) or keep your computer and terminal running at all times.

Again, the [Quick Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/quick-install-script) is a very simple command to deploy in one go. No need to learn Docker or Helm in depth! You will need a Linux server as described in the [Requirements](https://rasa.com/docs/rasa-x/installation-and-setup/install/quick-install-script#hardware--os-requirements) though.

Nonetheless, interesting project and good luck 🙂 We are always happy to help on the Forum!

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 7:29pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/17 "2021-08-29T19:29:54Z")

</div>

I’m running a Debian / NodeJS server from Amazon AWS The front-end is primarily vanilla JavaScript with jQuery

---

<div class="post-metadata">

**Author:** ![bferster](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/bferster/32/16714_2.png) [@bferster](https://forum.rasa.com/u/bferster)\
**Post date:** [August 29, 2021, 7:31pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/18 "2021-08-29T19:31:12Z")

</div>

Chris, The link you shared is for rasa- x, but I’m using rasa open-source. Is there a tutorial for that?

---

<div class="post-metadata">

**Author:** ![ChrisRahme](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/chrisrahme/32/15572_2.png) [@ChrisRahme](https://forum.rasa.com/u/ChrisRahme)\
**Post date:** [August 29, 2021, 7:33pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/19 "2021-08-29T19:33:06Z")

</div>

It’s for Rasa X as well as Rasa Open Source. The [Quick Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/quick-install-script) will install both.

If you want Rasa Open Source only you will have to go with the more complicated [Docker Compose Installation](https://rasa.com/docs/rasa-x/installation-and-setup/install/docker-compose) I believe.

Rasa X is just a nice interface to manage the chatbot 🙂

You can watch [this](https://www.youtube.com/watch?v=qaF6BTjY46E) tutorial which shows Quick Installation on GCP. Even though you use AWS, the process is similar.

---

<div class="post-metadata">

**Author:** ![nik202](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/nik202/32/16098_2.png) [@nik202](https://forum.rasa.com/u/nik202)\
**Post date:** [August 29, 2021, 7:36pm UTC](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284/20 "2021-08-29T19:36:24Z")

</div>

> [@bferster](#):
>
> Amazon AWS

@bferster Do check this also may be it will help you : [https://youtu.be/ko9-zPDuhQo](https://youtu.be/ko9-zPDuhQo)

@bferster Do check this also [https://youtu.be/tasoWTGM1hA](https://youtu.be/tasoWTGM1hA)

@bferster Docker will be easy pizzy for you, I believe that.

[Next page](https://forum.rasa.com/t/run-rasa-server-directly-not-from-a-source-environment/47284.md?page=2)
