15 commits

Author	SHA1	Message	Date
Ohad Livne	69d53d4d8a	Increase the cache TTL for loaded models	2026-04-20 00:24:11 +03:00
Ohad Livne	bebbefcda7	Support health checks for the services	2026-04-20 00:24:09 +03:00
Ohad Livne	7be6bccbc9	Check for image updates on startup	2026-04-20 00:24:08 +03:00
Ohad Livne	36a16cc1dd	Only expose access ports on the localhost network	2026-04-20 00:24:08 +03:00
Ohad Livne	2a383a6c3c	Restrict service container privileges	2026-04-20 00:24:07 +03:00
Ohad Livne	0503aed013	Enable auto updates for the service containers	2026-02-07 00:26:41 +02:00
Ohad Livne	c2e29a3bfe	Increase the cache TTL for loaded models	2026-02-07 00:26:37 +02:00
Ohad Livne	619a6e7f3a	Run service containers in the transient store for speed and safety	2026-02-07 00:26:35 +02:00
Ohad Livne	c4bc942307	Use a read-only root filesystem in service containers	2026-02-07 00:26:35 +02:00
Ohad Livne	cd5958bd21	Use long option names	2026-02-07 00:26:32 +02:00
Ohad Livne	57ea018567	Start the Ollama server automatically on boot	2026-02-07 00:26:19 +02:00
Ohad Livne	2bf4debbc3	Isolate the LLM server from the internet	2026-02-07 00:26:17 +02:00
Ohad Livne	a6fee6113f	Revoke unnecessary filesystem permissions for the server	2026-02-07 00:26:17 +02:00
Ohad Livne	8a0698f5b4	Keep the models in a persistent volume	2026-02-07 00:26:16 +02:00
Ohad Livne	531a16fa93	Declare a quadlet file for an Ollama server	2026-02-07 00:26:13 +02:00