move ai notes from framework_desktop to software_ai_stack

active/software_ai_stack/quadlets_guest/llama-embed.container

@@ -0,0 +1,39 @@
+[Unit]
+Description=A Llama CPP Server running an Embedding Model
+
+[Container]
+# Shared AI internal pod
+Pod=ai-internal.pod
+
+# Image is built locally via podman build
+Image=localhost/llama-cpp-vulkan:latest
+
+# Downloaded models volume
+Volume=/home/ai/models/embedding:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Server command
+Exec=--port 8001 \
+    --n-gpu-layers all \
+    --embeddings \
+    -m /models/nomic-embed-text-v2/nomic-embed-text-v2-moe-q8_0.gguf
+
+# Health Check
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8001/props || exit 1
+HealthInterval=10s
+HealthRetries=3
+HealthStartPeriod=10s
+HealthTimeout=30s
+HealthOnFailure=kill
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/software_ai_stack/quadlets_guest/open-webui-guest.container

@@ -0,0 +1,32 @@
+[Unit]
+Description=An Open Webui Frontend for Local AI Services for Guests
+
+[Container]
+# Shared AI external pod
+Pod=ai-external.pod
+
+# Open Webui base image
+Image=ghcr.io/open-webui/open-webui:main
+
+# Nothing too complicated here. Open Webui will basically configure itself.
+Volume=open-webui-data-guest:/app/backend/data
+
+# WEBUI_SECRET_KEY is required to prevent logout on Restart
+EnvironmentFile=/home/ai/.env/open-webui-env-guest
+
+# ai-external is the primary network
+Network=ai-external.network
+Network=ai-internal.network
+
+# open-webui
+PublishPort=8081:8081/tcp
+
+[Service]
+Restart=on-failure
+RestartSec=5
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target