7 ways GPT-4 with Vision can uplevel your Streamlit apps

Is there a way to use an st.button to capture a screenshot of the app and send the screenshot to a multi-modal LLM?

This would be quite helpful for creating a “copilot” chatbot that could visualize what the user is plotting (or visualize warnings) and provide suggestions to the user.

I guess that there is Streamlit Screenshots, but it would be great to have a more integrated way of providing streamlit screenshots to a multi-modal LLM.

1 Like