docs(guide): run ML on another machine (#3335)

* Add documentation for hosting the ML container on a different machine

* Revert "Add documentation for hosting the ML container on a different machine"

This reverts commit 11e635eb57.

* Moved to Guides section and removed .env file reference

docs/docs/guides/machine-learning.md

@@ -0,0 +1,26 @@
+# Hosting the machine-learning service on another system
+
+To alleviate [performance issues on low-memory systems](/docs/FAQ.md#why-is-immich-slow-on-low-memory-systems-like-the-raspberry-pi) like the Raspberry Pi, you may also host Immich's machine-learning container on a more powerful system (e.g. your laptop or desktop computer):
+
+- Set `IMMICH_MACHINE_LEARNING_URL` to point to the designated ML system, e.g. `http://workstation:3003`.
+- Copy the following `docker-compose.yml` to your ML system.
+- Start the container by running `docker-compose up -d` or `docker compose up -d` (depending on your Docker version).
+
+```yaml
+version: '3.8'
+
+services:
+  immich-machine-learning:
+    container_name: immich_machine_learning
+    image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
+    volumes:
+      - model-cache:/cache
+    restart: always
+    ports:
+      - 3003:3003
+
+volumes:
+  model-cache:
+```
+
+Please note that version mismatches between both hosts may cause instabilities and bugs, so make sure to always perform updates together.