Скачать или смотреть How To Setup Open WebUI And Run Any AI LLM ChatBot On A DigitalOcean GPU Cloud Server

In this video, you will learn how to make an Open WebUI server and run any artificial intelligence (AI) model of your choosing on a GPU cloud server. Open WebUI is an open-source web interface enabling simple interaction with LLMs The cloud server host provider chosen for this video tutorial is DigitalOcean, which allows for easy creation of GPU cloud servers with pre-configured AI large language models (LLMs) through its GPU Droplet service. DigitalOcean also has a service called droplets which are regular cloud servers or virtual private servers (VPS). This service allows for simple 1-click installation of the Open WebUI app from DigitalOcean's marketplace. These two services (GPU Droplet containing your AI model and Droplet containing Open WebUI) must then be linked by setting an inference endpoint to allow Open WebUI to auto-detect your AI model(s).

🔵Free $200 DigitalOcean cloud credits using my referral link: https://m.do.co/c/89b2c5ca8ec4

How To Get $200 In Free DigitalOcean Cloud Credits    • How To Get $200 In Free DigitalOcean Cloud...  

How To Generate A SSH Public And Private Key Pair Using PuTTYgen To Connect To Your VPS    • How To Generate A SSH Public And Private K...  

Download PuTTYgen To Generate SSH Key Pairs https://www.putty.org/

How To Install PuTTY on Windows 11 And Windows 10    • How To Install PuTTY On Windows 10 Or Wind...  

Steps To Make An Open WebUI Server And Run Any AI LLM On A Cloud GPU:
1. Go to https://m.do.co/c/89b2c5ca8ec4 and create a free DigitalOcean account. The above link is my referral link granting you $200 in free cloud credit for 60 days as a new user
2. On your projects dashboard, click create and select GPU Droplets
3. Configure your GPU droplet to your liking, ensuring to select one of the 1-click model images pre-configured by Hugging Face (Hugs or HF)
4. Add a Public SSH Key for authentication. You can generate an SSH public and private key pair by following this step by step video of mine    • How To Generate A SSH Public And Private K...  
5. Choose a unique name for your GPU droplet and click Create GPU Droplet
6. Click create and select Dropets
7. Configure your droplet to your liking, ensuring to select the 1 click marketplace app called Open WebUI
8. Choose an authentication method and a hostname for your droplet and click on Create Droplet
9. Copy your Open WebUI droplets IP address from the DigitalOcean dashboard and open up a new tab
10. Type the following into the URL address bar of your browser:

http://Open_WebUI_Droplets_IPv4_Address:3000
e.g. http://162.243.107.47:3000

11. Create your Open WebUI servers admin account
12. To set the inference endpoint, click on your Open WebUI profile picture at the top right
13. Click Settings
14. Click Admin Settings
15. Click Connections
16. Underneath Manage OpenAI API Connections, remove the default link and type the following ensuring to copy your GPU droplets IP address:

http://GPU_Droplet_IPv4_Address/v1
e.g. http://107.170.36.191/v1

17. To fill in the API key you will need to grab the Bearer Token from your GPU droplet, click on your GPU droplets name
18. Click Web Console on the right hand side and a new browser window will open
19. Copy your GPU droplets unique Bearer Token from the message of the day (MOTD)
20. Go back to the Open WebUI dashboard and paste in the bearer token into the API key section
21. Click the configure icon which is a nut or gear icon
22. Click the Verify Connection icon which looks like a refresh icon to check the connection between your Open WebUI droplet and your GPU droplet which has your desired AI model installed. If they are linked and communicating with each other you will see the green message which says "Server Connection Verified". This will allow Open WebUI to automatically detect and use available models on your GPU server
23. Click Save to saved the edited connection details
24. Click on the Ollama API toggle to disable it
25. Click Save to update all API connection settings
26. Click on the three horizontal lines at the top left corner
27. Open WebUI will then display and select your AI model(s) that you have installed on your GPU droplet
28. To interact with your AI model, click on the text box to start a new chat
29. Enter your message and press enter on your keyboard to send your message
30. The AI will then respond to your message.

Timestamps:
0:00 - Intro & Context
1:09 - Create GPU Droplet With Chosen AI Model
5:09 - Create Droplet With Open WebUI 1-Click Marketplace App
7:44 - Create Open WebUI Admin Account
9:06 - Set Inference Endpoint - Add API Base URL & Bearer Token (API Key)
11:43 - Interact With The AI Model
12:29 - Closing & Outro

More DO Guides (Playlist)    • DigitalOcean Cloud Computing Guides  

AI, ML, & LLMs Tutorials (Playlist)    • Artificial Intelligence (AI), Machine Lear...  

SUBSCRIBE    / @websplaining  
Personal Website https://www.websplaining.com

#OpenWebUI #GpuDroplet #DigitalOcean