Update backend/query_llm.py

backend/query_llm.py

@@ -104,6 +104,7 @@ def generate_hf(prompt: str, history: str, temperature: float = 0.9, max_new_tok
                                             stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream:
+            print(response.token.text)
             output += response.token.text
             yield output
 
@@ -205,6 +206,7 @@ def generate_gemini(prompt: str, history: str, temperature: float = 0.9, max_new
                                             stream=True)
         output = ""
         for response in stream:
+            print(response.text)
             output += response.text
             yield output