Update app.py

app.py

@@ -1,10 +1,52 @@
 import gradio as gr
+from fastapi import FastAPI
+from pydantic import BaseModel
+import requests
 
+# -----------------
+# Gradio UI
+# -----------------
 with gr.Blocks(fill_height=True) as demo:
     with gr.Sidebar():
         gr.Markdown("# Inference Provider")
-        gr.Markdown("This Space showcases the open-r1/OlympicCoder-7B model, served by the featherless-ai API. Sign in with your Hugging Face account to use this API.")
+        gr.Markdown(
+            "This Space showcases the open-r1/OlympicCoder-7B model, "
+            "served by the featherless-ai API. Sign in with your Hugging Face "
+            "account to use this API."
+        )
         button = gr.LoginButton("Sign in")
+
     gr.load("models/open-r1/OlympicCoder-7B", accept_token=button, provider="featherless-ai")
-    
-demo.launch()
+
+# -----------------
+# FastAPI backend for API
+# -----------------
+app = FastAPI()
+
+class Query(BaseModel):
+    text: str
+    token: str = None  # Optional HF token if needed
+
+@app.post("/predict")
+def predict(query: Query):
+    """Call the Hugging Face inference API for the model."""
+    api_url = "https://api-inference.huggingface.co/models/open-r1/OlympicCoder-7B"
+    headers = {}
+    if query.token:
+        headers["Authorization"] = f"Bearer {query.token}"
+
+    payload = {"inputs": query.text}
+    response = requests.post(api_url, headers=headers, json=payload)
+
+    if response.status_code == 200:
+        try:
+            result = response.json()
+            return {"response": result}
+        except Exception:
+            return {"error": "Invalid JSON response from model"}
+    else:
+        return {"error": response.text}
+
+# Mount Gradio app inside FastAPI
+app = gr.mount_gradio_app(app, demo, path="/")
+