A newer version of the Streamlit SDK is available:
1.40.1
metadata
title: Llama Index Docs Spaces
emoji: 📚
colorFrom: purple
colorTo: indigo
sdk: streamlit
sdk_version: 1.28.2
app_file: app.py
pinned: false
How to pick chunks that are pertinent, ie help the model respond ? How to stream response word by word ?