Streamlit¶

Streamlit is an open-source Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science. It uses an integrated cloud based IDE with integration to github codespaces and deploy on streamlit SaaS servers.

See Getting started

Main concepts¶

• Use a CLI to start an Streamlit server.

streamlit run your_script.py
# or 
python -m streamlit run your_script.py
# or using a script in a git url
streamlit run https://raw.githubusercontent.com/streamlit/demo-uber-nyc-pickups/master/streamlit_app.py

• Support continuous interactive loop development experience
• Can present Pandas dataframe directly in the page withing a table widget.
• Streamlit makes it easy to organize the widgets in a left panel sidebar with st.sidebar.
• It supports Light and Dark themes out of the box, and custom theme.
• Support multiple pages application.

Samples¶

• Getting Started with matching code to test it.
• Run the app in Docker, see the Dockerfile in this project / folder (llm-ref-arch-demo/sa-tools/user-interface)
• Some best practices here.
• Streamlit Cheat Sheet app in Streamlit.

Some How To¶

pdf = st.file_uploader('Upload your PDF Document', type='pdf')
if pdf is not None:
    reader = PdfReader(pdf)

    if save_button:
        data={"callWithVectorStore":callWithVectorStore, "callWithDecisionService": callWithDecisionService, "llm_provider": llm_provider }
        st.write(data)
        st.session_state["app_config"]=data

if 'app_config' not in st.session_state:
st.session_state['app_config']= {
    "callWithVectorStore":False, 
    "callWithDecisionService": False, 
    "llm_provider": "openAI" 
    }

app_config=st.session_state['app_config']