Update backend/query_llm.py

backend/query_llm.py

@@ -106,8 +106,8 @@ def generate_hf(prompt: str, history: str, temperature: float = 0.9, max_new_tok
         for response in stream:
             print(response.token.text)
             output += response.token.text
-        return output
-            #yield output
+            #return output
+            yield output
 
     except Exception as e:
         if "Too Many Requests" in str(e):