This revision is from 2024/08/09 09:53. You can Restore it.

sudo apt update
Copy

sudo apt install docker.io
Copy

sudo systemctl start docker
sudo systemctl enable docker
Copy

sudo usermod -aG docker $USER
sudo chown $USER:$USER /var/run/docker.sock
Copy

Have an Nvidia or compatible GPU?

sudo lshw -c display
Copy

If you have compatible GPU

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

otherwise use the CPU

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
Copy

Remove the failed GPU installation if you incorrectly installed the GPU version without having a compatible GPU

docker rm open-webui
Copy

Rerun either the GPU or CPU version command above. docker run...

After installation, you can access Open WebUI at http://localhost:3000

More commands...

docker stop open-webui
docker restart open-webui
Copy

curl -fsSL https://ollama.com/install.sh | sh
Copy

You go to the website and get the model command and then goto settings in the webui and put the command in Pull a model from Ollama.com

Other Web UI's

https://github.com/huggingface/chat-ui - Amazing clean UI with very good web search, my go to currently. (they added the ability to do it all locally very recently!)

https://github.com/oobabooga/text-generation-webui - Best overall, supports any model format and has many extensions

https://github.com/ParisNeo/lollms-webui/ - Has PDF, stable diffusion and web search integration

https://github.com/h2oai/h2ogpt - Has PDF, Web search, best for files ingestion (supports many file formats)

https://github.com/SillyTavern/SillyTavern - Best for custom characters and roleplay

https://github.com/NimbleBoxAI/ChainFury - Has great UI and web search (experimental)

https://github.com/nomic-ai/gpt4all - Basic UI that replicated ChatGPT

https://github.com/imartinez/privateGPT - Basic UI that replicated ChatGPT with PDF integration

More from the comments (Haven't tested myself) :

https://github.com/LostRuins/koboldcpp - Easy to install and simple interface

LM Studio - Clean UI, focuses on GGUF format

https://github.com/lobehub/lobe-chat - Nice rich UI with the ability to load extensions for web search, TTS and more

https://github.com/ollama-webui/ollama-webui - ChatGPT like UI with easy way to download models

https://github.com/turboderp/exui - very fast and vram efficient

https://github.com/PromtEngineer/localGPT - Focuses on PDF files

https://github.com/shinomakoi/AI-Messenger - Supports EXLv2 and LLava

Documentation - Vercel AI SDK - NodeJS/Reactive

docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower --run-once open-webui
Copy

sudo apt update
sudo apt upgrade
sudo systemctl start docker
sudo systemctl enable docker
docker --version
Copy

sudo curl -L "https://github.com/docker/compose/releases/download/v2.21.0/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
export PATH=/usr/local/bin:$PATH
docker-compose --version
Copy

docker-compose up -d
Copy

docker-compose down
Copy

docker-compose up --build
Copy