app.py

app.py

@@ -2,11 +2,12 @@ import gradio as gr
 from transformers import pipeline
 from fastapi import FastAPI, Request
 from fastapi.responses import JSONResponse
+import uvicorn
 
 # ===== Load the model =====
 model = pipeline("text-generation", model="microsoft/DialoGPT-medium")
 
-# ===== Define chatbot logic =====
+# ===== Chat function =====
 def chat(message):
     if not message.strip():
         return "⚠️ Please enter a message."
@@ -14,7 +15,7 @@ def chat(message):
     reply = result[len(message):].strip()
     return reply or "🤖 Sorry, I didn’t quite catch that."
 
-# ===== Gradio Interface =====
+# ===== Gradio app =====
 demo = gr.Interface(
     fn=chat,
     inputs=gr.Textbox(label="Message"),
@@ -23,9 +24,10 @@ demo = gr.Interface(
     description="Smart, adaptive chatbot powered by Hugging Face"
 )
 
-# ===== FastAPI backend to expose /api/predict =====
-app = FastAPI()
+# ===== Create FastAPI app =====
+app = FastAPI(title="Savenzer AI API", version="2.0")
 
+# ===== Add custom /api/predict route =====
 @app.post("/api/predict/")
 async def predict(request: Request):
     try:
@@ -36,11 +38,9 @@ async def predict(request: Request):
     except Exception as e:
         return JSONResponse({"error": str(e)}, status_code=500)
 
-# ===== Mount Gradio app =====
-gr_app = gr.routes.App.create_app(demo)
-app.mount("/", gr_app)
+# ===== Mount Gradio UI to root =====
+app = gr.mount_gradio_app(app, demo, path="/")
 
-# ===== Launch manually (only for local testing) =====
+# ===== Local run only (not needed on Hugging Face) =====
 if __name__ == "__main__":
-    demo.queue()
-    demo.launch(show_api=False)
+    uvicorn.run(app, host="0.0.0.0", port=7860)