Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# connecting to the model so my chatbot can generate real responses
+# connecting to the model so my chatbot can generate real AI responses
 client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")
 
 def respond(message, history):
@@ -15,21 +15,15 @@ def respond(message, history):
                 "Keep responses under 100 words. "
                 "Be specific, clear, and briefly explain why each recommendation fits."
             )
+        },
+        {
+            "role": "user",
+            "content": message
         }
     ]
 
-    # adding the chat history so the chatbot can remember the conversation
-    # this format works with the Gradio version my Space is using
-    if history:
-        for user_msg, bot_msg in history:
-            messages.append({"role": "user", "content": user_msg})
-            messages.append({"role": "assistant", "content": bot_msg})
-
-    # adding the newest message from the user
-    messages.append({"role": "user", "content": message})
-
-    # i chose 0.7 because it gives a balance between creative and focused answers
-    # i used 150 max tokens so the response is long enough but still not too wordy
+    # i chose 0.7 because it balances creative and focused answers
+    # i used 150 max tokens so responses do not get cut off but also stay concise
     response = client.chat_completion(
         messages=messages,
         max_tokens=150,