Skip to content

edgible ai

Manage Ollama AI service

Setup Ollama AI and optionally expose via Edgible platform

Terminal window
edgible ai setup [flags]
FlagDescription
--model <model>Model to use (skips interactive selection)
--auto-installAutomatically install Ollama without prompting
--local-onlySkip platform integration (local setup only)
--expose-ollamaExpose Ollama API publicly
--setup-webuiSetup Open WebUI interface
--device-id <id>Serving device ID for both apps
--ollama-device-id <id>Serving device ID for Ollama
--webui-device-id <id>Serving device ID for Open WebUI
--gateway-ids <ids>Comma-separated gateway device IDs
--webui-deployment <type>WebUI deployment: local or remote
--non-interactiveRun in non-interactive mode

Stop Ollama service

Terminal window
edgible ai stop [flags]

Start Open WebUI connected to local Ollama service

Terminal window
edgible ai serve [flags]
FlagDescription
--port <port>WebUI port (default: 3200)
--ollama-url <url>Override Ollama URL (default: auto-detect host)
-d, --detachedRun in detached mode (default: true)

Stop AI services and optionally remove platform applications

Terminal window
edgible ai teardown [flags]
FlagDescription
--stop-ollamaAlso stop the Ollama service
--remove-volumesRemove data volumes (deletes all data)

Check status of AI services (Ollama and Open WebUI)

Terminal window
edgible ai status [flags]

Test Ollama model connectivity and response

Terminal window
edgible ai test [flags]
FlagDescription
--model <model>Model name to test (optional, tests first available if not specified)