Carson Sievert

LLM-powered chat is becoming a core pattern in modern Shiny apps, but building a good chat experience (i.e., streaming, history, file attachments, editing, cancellation, etc) — is harder than it looks.

Large Language Models (LLMs) are transforming how we build applications, but the path from "cool demo" to "production-ready tool" is littered with challenges: hallucinations, verifiability, and more. This tutorial covers the basics of how to build AI apps that avoid these challenges, yet are still effective and simple to build.

LLMs are powerful, but their knowledge is frozen — they can't access your private documents or recent information. Retrieval-Augmented Generation (RAG) solves this by searching relevant documents and including them in the prompt, grounding responses in real information.

Most Python packages that provide interactive web-based visualizations (e.g., altair, plotly, bokeh, ipyleaflet, etc.) can render in Jupyter notebooks via the ipywidgets standard.