Update app.py

app.py

@@ -333,12 +333,12 @@ async def chat_fn(query: Query):
 
     # Run blocking inference in thread
     loop = asyncio.get_event_loop()
-    response = await loop.run_in_executor(executor,
-                                          lambda: pipe(prompt,
-                                                        max_new_tokens=512,
-                                                        temperature=0.7,
-                                                        do_sample = True,
-                                                        top_p=0.9)[0]['generated_text']
+    response = await loop.run_in_executor(executor, lambda: pipe(prompt,
+                                                                 max_new_tokens=512,
+                                                                 temperature=0.7,
+                                                                 do_sample=True,
+                                                                 top_p=0.9)[0]['generated_text'])
+
 
     # Parse answer
     answer = response.split("Answer:")[-1].strip() if "Answer:" in response else response.split("الإجابة:")[-1].strip()