Update app.py

app.py

@@ -52,10 +52,12 @@ client = InferenceClient(api_key=hf_token)
 
 # Function to handle user inputs and fetch model responses
 def chatbot(input_text, history=[]):
-    messages = [{"role": "user", "content": input_text}]
+    #messages = [{"role": "user", "content": input_text}]
+    messages = []
     for user_input, bot_response in history:
         messages.append({"role": "user", "content": user_input})
         messages.append({"role": "assistant", "content": bot_response})
+    messages.append({"role": "user", "content": input_text})
 
     stream = client.chat.completions.create(
         model="google/gemma-2-2b-it", 
@@ -68,6 +70,8 @@ def chatbot(input_text, history=[]):
 
     # Concatenate streamed response
     bot_response = "".join(chunk.choices[0].delta.content for chunk in stream)
+
+    # Update conversation history
     history.append((input_text, bot_response))
     return bot_response, history