This example shows how we can use the streaming API to respond to return quicker results to the user and build a more seamless interactive experience.

This is the same chatbot as the one in the chatbot example, but it is built slightly differently (for streaming purposes).

Run streamlit run streamlit_app.py from the command line and you will see the chatbot in action. Open up the burr UI burr and you can track the chatbot.

We also have an async version in async_application.py which demonstrates how to use streaming async. We have not hooked this up to a streamlit application yet, but that should be trivial.

The notebook also shows how things work.