Update main.py

main.py

@@ -44,12 +44,12 @@ async def generate_text(request: Request, prompt: str = Body()):
         details=True, 
         return_full_text=False
     )
-    output = ""
+    # output = ""
 
-    for response in stream:
-        output += response.token.text
-        yield output
-        print(f"output + {output}")
-    return output
+    # for response in stream:
+    #     output += response.token.text
+    #     yield output
+    #     print(f"output + {output}")
+    # return output
 
-    # return response
+    return response