# Quick deploy tutorials

We have a few quick deploy tutorials available.

## Chatbot

In the Quick Deploy menu you have access to a chat-bot image with an Open WebUI web interface and inbuilt support for Ollama. 


![chatbot](../imgs/chatbot.png "Chatbot")

Click **Deploy** and wait for the image to be downloaded and for the job to start. Once it is running, open the terminal - see Terminal in the [Jobs tutorial](./jobs.md) for more detailed instructions.

You can pull any model supported by Ollama. You can check the current list of provided models on [Ollama's website](https://ollama.com/library) to choose the one that best suits your needs.

Inside the terminal, run: 
'''bash
ollama pull modelname
'''

![ollama-pull](../imgs/ollama_pull.png "Ollama pull")

Where you substitute modelname with the model you want to pull. 

Open the Job details view and open port 8080 as an open port - see [Exposing ports](./ports.md) for detailed instructions on how to do it. 
This will create a hyperlink in the **Addresses** field that will take you to your instance of the chatbot. 

![webui-port](../imgs/webuiport.png "WebUI port")

Create an account - the first user will always register as an admin. 

![admin-chat](../imgs/adminchat.png "Admin registration Open WebUI")


The models you pulled in the previous step will be available there. Feel free to chat, upload files to create your own knowledge base, and explore other features that Open WebUI has to offer! 

Keep in mind that all your data is saved inside a running container and will disappaer once the running job has ended. 


## Matlab using image from NGC
Here we will run a job using the [Matlab image from ngc](https://catalog.ngc.nvidia.com/orgs/partners/containers/matlab) and connect to it in our webbrowser. This image have two ports that are interesting to expose:
- 5901 for VNC connections
- 6080 for webbrowser

In this tutorial we will expose 6080 on the container a running job, and connect to it using a private connection that only our user has access to. To do this go to the Jobs page and enter the following parameters:
- Job label: Our matlab job
- Number of GPUs: 1
- Time: 60
- Image: partners/matlab:r2021a
- Ports: 6080

![matlab-job](../imgs/matlabjob.png "Matlab")

Hit the "Queue Job" button and wait for the job to start.

After the job has start click on its entry in the "Queue & Jobs history" table to bring up the job information. From here you can see the port in the table, but the port has not yet been opened. To open it click on the three dots in the "Actions" column and select "Open private".

![private-port](../imgs/openprivate.png "Open private port")

This will open the port for the current user only and provide an address to access it in the table. **NOTE** that this uses cookies for authentication, so if your webbrowser is rejecting the cookies this method will not work. In that case you can use a public port and set the IP-filter to only allow traffic from your address.

![port-address](../imgs/portaddress.png "Port address")

Clicking on the address will take you a webpage that is hosted inside the container.

![matlab-gui](../imgs/matlabgui.png "Matlab GUI")

To open matlab you can click on the matlab icon up in top right. You will need a matlab account which I do not have :( So instead I just fire up a terminal and watch star wars.

![star-wars](../imgs/starwars.png "Star wars")