Create entrypoint.sh

entrypoint.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+# Start Ollama in the background
+ollama serve &
+
+# Pull the model (runs only if not already downloaded)
+ollama pull hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
+
+# Start the FastAPI server
+uvicorn app:app --host 0.0.0.0 --port 8000