Update app.py

app.py

@@ -6,7 +6,7 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token="hf_gzFQTPmbxocKx
 
 def send_message(message):
     messages = [{"role": "user", "content": message}]
-    response = client.chat_completion(messages, max_tokens=150, stream=True)
+    response = client.chat_completion(messages, max_tokens=150)
     return response
 
 def main():
@@ -17,10 +17,10 @@ def main():
     
     if st.button("Send"):
         with st.spinner('AI is typing...'):
-            # Send message and display response incrementally
-            for token in send_message(user_input):
-                for choice in token.choices:
-                    st.write(choice.delta.content, end="")
+            response = send_message(user_input)
+            # Display complete response
+            for choice in response.choices:
+                st.write(choice.message.content)
 
 if __name__ == "__main__":
     main()