Convert to Gradio Space to bypass Docker paywall

README.md

@@ -3,8 +3,8 @@ title: PACE AI Inference
 emoji: 🚀
 colorFrom: blue
 colorTo: indigo
-sdk: docker
-app_port: 7860
+sdk: gradio
+app_file: app.py
 ---
 
 # PACE AI Inference Service

main.py → app.py

@@ -7,13 +7,13 @@ from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
 import threading
 
-app = FastAPI(
+fastapi_app = FastAPI(
     title="PACE AI Inference Service",
     description="Hugging Face Deployment for PACE Actor-Critic Ensemble",
     version="1.0.0"
 )
 
-app.add_middleware(
+fastapi_app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
     allow_credentials=True,
@@ -28,15 +28,15 @@ class GenerateRequest(BaseModel):
 
 _generate_lock = threading.Lock()
 
-@app.get("/")
+@fastapi_app.get("/")
 def root():
     return {"status": "PACE AI Service Running"}
 
-@app.get("/health")
+@fastapi_app.get("/health")
 def health():
     return {"status": "healthy"}
 
-@app.post("/generate_stream")
+@fastapi_app.post("/generate_stream")
 def generate_stream(request: GenerateRequest):
     def event_stream():
         if not _generate_lock.acquire(blocking=False):
@@ -67,3 +67,10 @@ def generate_stream(request: GenerateRequest):
             _generate_lock.release()
 
     return StreamingResponse(event_stream(), media_type="application/x-ndjson")
+
+import gradio as gr
+demo = gr.Blocks()
+with demo:
+    gr.Markdown("# PACE AI Backend Running\nThis is a FastAPI backend running inside a Gradio Space.")
+
+app = gr.mount_gradio_app(fastapi_app, demo, path="/ui")