Run Llama 2, Code Llama, and other models. Customize and create your own.

## Configuration

open-webui accepts the following configuration keys & values (which you can modify with sudo snap set open-webui <key>=<value>)

• data-dir (default: $SNAP_COMMON, i.e. /var/snap/open-webui/common/data)
• enable-signup (default: true)
• host (default: 0.0.0.0)
• ollama-api-base-url (default: http://localhost:11434/api)
• openai-api-base-url (default: https://api.openai.com/v1)
• openai-api-key (default: "")
• port (default: 8080)
• secret-key (generated at install time)

## open-webui and ollama

open-webui works with [ollama](https://ollama.com) out of the box, as long as ollama is installed. Simplest way to install ollama with settings that will work with open-webui: sudo snap install ollama --channel=beta

## Features

• Starts the systemd service (ollama serve) automatically at install time.
• Offers configuration keys (respected by both the ollama command line tool as well as the systemd service):
  • sudo snap set ollama host=... to set OLLAMA_HOST (see https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-expose-ollama-on-my-network)
  • sudo snap set ollama models=... to set OLLAMA_MODELS(see https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-set-them-to-a-different-location)
  • sudo snap set ollama origins=... to set OLLAMA_ORIGINS with default value "*://localhost" (see https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-allow-additional-web-origins-to-access-ollama)