thelocallab/ollama-openwebui repository overview

⁠Ollama and Open WebUI Dockerfile

This Dockerfile sets up an environment for running Ollama, an open-source large language model runner, along with Open WebUI, a web interface for interacting with AI models.

⁠Video Tutorial

⁠Features

• Based on Python 3.11
• Installs Ollama directly in the container
• Sets up Open WebUI for easy interaction with AI models
• Downloads the qwen2.5-coder:1.5b model
• Exposes ports 8080 and 11434 for web access and API communication

⁠Prerequisites

• Docker installed on your system

⁠Usage

1. Build the Docker image:

   docker build -t ollama-webui .
   

   Copy
2. Run the container:

   docker run -p 8080:8080 -p 11434:11434 ollama-webui
   
   

   Copy
3. Access the Open WebUI interface by navigating to http://localhost:8080⁠ in your web browser.

⁠What's Included

• Python 3.11: The base image for the container.
• Ollama: An open-source large language model runner.
• Open WebUI: A web interface for interacting with AI models.
• qwen2.5-coder:1.5b model: A pre-downloaded AI model for immediate use.

⁠Startup Process

The container's startup script performs the following actions:

1. Starts the Ollama server in the background
2. Installs Open WebUI
3. Downloads the specified AI model
4. Sets the necessary environment variable for WebUI
5. Starts the Open WebUI server

⁠Ports

• 8080: Exposed for accessing the Open WebUI interface
• 11434: Exposed for API communication with Ollama

⁠Customization

To use a different AI model, modify the ollama pull command in the start.sh script within the Dockerfile. Note

Ensure your system has sufficient resources to run the AI model, as large language models can be resource-intensive.