The Ollama Web UI project was renamed!
I had a look to it as ex ollama web ui
And now its called Open Web UI.
- The Ollama web UI Official Site
- The Ollama web UI Official Site
- The Ollama web UI Official Site
- The Ollama web UI Source Code at Github
- License: MIT ❤️
Have a look to the docs for further config: https://docs.openwebui.com/getting-started/quick-start/
Generally, we just need something simple, like:
docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
But there are additional tweaks via env variable:
# docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
# docker run -d -p 3000:8080 -e WEBUI_AUTH=False -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main
This docker-compose.yml
will make it easier if you dont have Ollama running yet as container:
Use Ollama and OpenWebUI with one Stack⏬
version: '3'
services:
ollama:
image: ollama/ollama
container_name: ollama
ports:
- "11434:11434"
volumes:
- ollama_data:/root/.ollama
ollama-webui:
image: ghcr.io/ollama-webui/ollama-webui:main
container_name: ollama-webui
ports:
- "3000:8080" # 3000 is the port that you will access in your browser
# add-host:
# - "host.docker.internal:host-gateway"
volumes:
- ollama-webui_data:/app/backend/data
restart: always
volumes:
ollama_data:
ollama-webui_data:
Once both containers are running, you will be able to setup a Open Web UI admin user.
And then just go through:
Then, you might see such warning:
Which you can validate by going into ollama container:
docker exec -it ollama /bin/bash
#podman exec -it ollama /bin/bash
And do simply:
ollama --version
#ollama version is 0.5.7-0-ga420a45-dirty
So just make sure that both container can speak:
version: "3.8"
services:
ollama:
image: ollama/ollama
container_name: ollama
ports:
- "11434:11434" # Expose only if needed from outside the Docker network
volumes:
- ollama_data:/root/.ollama
networks:
- my-network
ollama-webui:
image: ghcr.io/ollama-webui/ollama-webui:main
container_name: ollama-webui
ports:
- "3000:8080" #The UI!
networks:
- my-network
environment:
- WEBUI_AUTH=False
- OLLAMA_BASE_URL=http://ollama:11434 # Use the container name as hostname
networks:
my-network:
volumes:
ollama_data:
ollama-webui_data:
https://www.youtube.com/watch?v=Wjrdr0NU4Sk
https://www.youtube.com/watch?v=16fWf0VVeIo
How to use Ollama to Text with your Docs
How to Integrate Open Web UI with Stable Difussion
https://www.youtube.com/watch?v=Wjrdr0NU4Sk
FAQ
Free Options to Chat with your Documents
- PrivateGPT
- LogSeq
- Reor - https://github.com/reorproject/reor
Free & Open Source Ways to Interact with LLMs
- TextgenwebUI
- KoboldCPP
- GPT4 ALL (requires python)
How to make LLMs work together
- CrewAI
- Fabric
How to make LLMs code for you
- Devin
- https://github.com/VRSEN/agency-swarm-lab
- Smoldev
- Tabby
- Continue