fix(ai): configure OLLAMA_KEEP_ALIVE=5m to automatically release RAM after inactivity

app/config.py

@@ -43,4 +43,5 @@ DB_PATH.parent.mkdir(parents=True, exist_ok=True)
 
 OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://127.0.0.1:11434").rstrip("/")
 OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "qwen2.5:3b")
+OLLAMA_KEEP_ALIVE = os.getenv("OLLAMA_KEEP_ALIVE", "5m")