Update backend/query_llm.py

backend/query_llm.py

@@ -162,8 +162,8 @@ def generate_openai(prompt: str, history: str, temperature: float = 0.9, max_new
         output = ""
         for chunk in stream:
             output += chunk.choices[0].delta.get("content", "")
-            yield output
-
+            #yield output
+        return output
     except Exception as e:
         if "Too Many Requests" in str(e):
             print("ERROR: Too many requests on OpenAI client")