A Gen AI Specialist is developing a Streamlit chatbot that uses `snowflake.cortex.complete` to answer user questions with this script:
```python
import streamlit as st
import snowflake.cortex
from snowflake.cortex import CompleteOptions
if prompt := st.chat_input("How can I help you?"):
with st.chat_message(name="User"):
st.write(prompt)
with st.chat_message("assistant"):
response = snowflake.cortex.complete(
"claude-3-5-sonnet",
[dict(role="user", content=prompt)],
)
```
Which parameter should be added to the script so responses display incrementally in small chunks as they are generated?
Submit