Update app.py

app.py

@@ -10,6 +10,7 @@ client = InferenceClient(model=current_model, token=HF_TOKEN)
 conversation_history = []
 
 def enhanced_chat_response(user_input, max_tokens, temperature, top_p):
+    print("inside enhanced_chat_response")
     if not user_input.strip():
         return "", "Bitte gib eine Nachricht ein.", "", ""
     
@@ -21,6 +22,7 @@ def enhanced_chat_response(user_input, max_tokens, temperature, top_p):
     
     
     messages = [system_prompt, {"role": "user", "content": user_input}]
+    
     # Hier printen wir die messages vor dem API-Aufruf
     print("Messages sent to API:", messages)
 
@@ -56,7 +58,7 @@ def enhanced_chat_response(user_input, max_tokens, temperature, top_p):
         for message in client.chat_completion(
             messages=messages,
             max_tokens=min(max_tokens, 100),
-            stream=True,
+            stream=False,
             temperature=temperature,
             top_p=top_p
         ):