checkpoint commit

active/software_ai_stack/llama-embed.container

@@ -2,7 +2,7 @@
 Description=A Llama CPP Server For Embedding Models
 
 [Container]
-# Shared AI internal pod
+# Shared AI internal pod without internet access
 Pod=ai-internal.pod
 
 # Image is built locally via podman build
@@ -18,21 +18,22 @@ AddDevice=/dev/dri
 # Server command
 Exec=--port 8001 \
     -c 0 \
+    -b 1024 \
+    -ub 1024 \
     --perf \
     --n-gpu-layers all \
-    --models-max 1 \
-    --models-dir /models \
     --embedding \
-    -m /models/qwen3-embed-4b/Qwen3-Embedding-4B-Q8_0.gguf \
+    -m /models/emebeddinggemma-300m/embeddinggemma-300M-BF16.gguf \
     --alias embed
 
 # Health Check
-HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8001/props || exit 1
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8001/health || exit 1
 HealthInterval=10s
 HealthRetries=3
 HealthStartPeriod=10s
 HealthTimeout=30s
 HealthOnFailure=kill
+EnvironmentFile=/home/ai/.llama-api/keys.env
 
 [Service]
 Restart=always
@@ -41,4 +42,4 @@ TimeoutStartSec=900
 
 [Install]
 # Start by default on boot
-WantedBy=multi-user.target default.target
+WantedBy=multi-user.target default.target