Installing OpenWebUI

Local AI that looks nice

https://go.screenpal.com/watch/cTVo09neS2A

Step 1: Download and INSTALL Docker (Docker.com). It will start running by default; give it a minute!

Step 2: Open Up Terminal

Step 3: Copy and paste this (from http://www.github.com/open-webui/open-webui

docker run -d -p 3000:8080 -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama

It will download a list of things then go back to the command prompt. Breathe a sigh of relief, you’re almost done!

Step 4: Now in Chrome/browser go to

localhost:3000

You’ll sign up to create an account for OpenWeb-UI that by default will be the Admin account

Step 5: Yay, but how do I chat!

On the top part where it says Model, start typing: “llama3.2:3b”; I’m assuming your computer isn’t state of the art so this model should work on ‘most’ - if it’s a little older use llama3.2:1b and you’ll be

generally ok still!

That’s ‘it’! Now you can chat away! Next up: Local “AI Agents”.

Notes:

If you’re wanting to create agents, I recommend inserting ‘download and install Ollama” as step 1.5, and then using this command that takes advantage of Ollama running as a layer underneath Open WebUI

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main