Setting up OpenWebUI and Ollama using Docker

1. A system with Docker installed

1. Open a terminal window.

2. Run the following command to install Ollama:

 curl https://ollama.ai/install.sh | sh

3. Verify the installation by running:

 ollama --version

Pull a language model (e.g., Llama 3) using Ollama:

 ollama pull llama3

1. Open a new terminal window.

2. Run the OpenWebUI Docker container:

 docker run -d --name openwebui \
   -p 3000:8080 \
   -e OLLAMA_API_BASE_URL=http://host.docker.internal:11434/api \
   --add-host host.docker.internal:host-gateway \
   ghcr.io/open-webui/open-webui:main

This command does the following:

1. Runs the container in detached mode (`-d`)

2. Names the container “openwebui” (`–name openwebui`)

3. Maps port 3000 on the host to port 8080 in the container (`-p 3000:8080`)

4. Sets the Ollama API base URL environment variable (`-e OLLAMA_API_BASE_URL=…`)

5. Adds a host entry to allow the container to communicate with the host machine (`–add-host …`)

6. Uses the OpenWebUI Docker image (`ghcr.io/open-webui/open-webui:main`)

1. Open a web browser and navigate to:

 http://localhost:3000

1. In the OpenWebUI interface, first create an account.

2. Login to the account created.

1. Start a new chat in OpenWebUI.

2. Select the language model you pulled earlier (e.g., Llama 3).

3. Send a test message to verify that everything is working correctly.

- To stop the OpenWebUI container:

docker stop openwebui

- To start the OpenWebUI container again:

docker start openwebui

- To remove the OpenWebUI container:

docker rm openwebui