Debug

Dockerfile

@@ -6,6 +6,7 @@ ENV PYTHONUNBUFFERED=1 \
     GRADIO_NUM_PORTS=1 \
     GRADIO_SERVER_NAME=0.0.0.0 \
     GRADIO_SERVER_PORT=7860 \
+    GRADIO_THEME=huggingface \
     PIP_NO_CACHE_DIR=1
 
 RUN apt-get update && \

app.py

@@ -3,6 +3,8 @@ from functools import lru_cache
 from typing import Any
 
 import gradio as gr
+from fastapi import FastAPI
+from fastapi.responses import HTMLResponse
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
 
@@ -194,10 +196,24 @@ with gr.Blocks() as demo:
     clear.click(clear_chat, outputs=[chat, message], show_api=False)
 
 
+app = FastAPI()
+
+
+@app.get("/healthz", response_class=HTMLResponse)
+def healthz() -> str:
+    return "<h1>Dreadzone health check OK</h1>"
+
+
+app = gr.mount_gradio_app(app, demo, path="/")
+
+
 if __name__ == "__main__":
-    demo.queue(max_size=8).launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        debug=True,
-        show_api=False,
+    gr.close_all()
+    import uvicorn
+
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=7860,
+        log_level="debug",
     )

requirements.txt

@@ -3,3 +3,4 @@
 gradio==5.49.1
 huggingface_hub>=0.23.0
 llama-cpp-python==0.3.29
+uvicorn[standard]>=0.30.0