Update backend/query_llm.py

backend/query_llm.py

@@ -108,7 +108,7 @@ def generate_hf(prompt: str, history: str, temperature: float = 0.5, max_new_tok
 def generate_qwen(formatted_prompt: str, history: str):
     response = client.predict(
                     query=formatted_prompt,
-                    history=[],
+                    history=history,
                     system='You are wonderful',
                     api_name="/model_chat"
                 )