Build LLM apps
Build AI assistants right into your data apps, answering questions over your data. Streamlit has chat with st.chat_input and st.chat_message, streaming responses with st.write_stream, step-by-step progress with st.status and st.expander (type="step" or type="compact"), and feedback on answers with st.feedback. Connect them to any model or agent framework, or to Cortex AI in Snowflake. To see these elements together, try the agent app demo. Your apps can also serve other AI agents as tools over MCP. For details, see Agent-accessible apps.
Build a basic chat app
Build a simple OpenAI chat app to get started with Streamlit's chat elements.
Build an LLM app using LangChain
Build a chat app using the LangChain framework with OpenAI.
Get chat response feedback
Buid a chat app and let users rate the responses. (thumb_up thumb_down)
Validate and edit chat responses
Build a chat app with response validation. Let users correct or edit the responses.
Still have questions?
Our forums are full of helpful information and Streamlit experts.