BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//speaker//ZDSTNC
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-scipy-2026-HFWAYG@pretalx.com
DTSTART;TZID=CST:20260713T133000
DTEND;TZID=CST:20260713T173000
DESCRIPTION:Large Language Models (LLMs) are transforming how we build appl
 ications\, but the path from "cool demo" to "production-ready tool" is lit
 tered with challenges: hallucinations\, verifiability\, and more. This tut
 orial covers the basics of how to build AI apps that avoid these challenge
 s\, yet are still effective and simple to build.\n\nWe'll start with [**qu
 erychat**](https://pypi.org/project/querychat/)\, an open-source package t
 hat lets users explore data through natural language. querychat demonstrat
 es a powerful pattern: rather than letting an LLM access raw data directly
  (where it can hallucinate calculations)\, it constrains the LLM to genera
 te SQL queries that are displayed and executed by a proper database engine
 . This "tool-based" architecture ensures reliability through transparency 
 and precision -- users see exactly what query was executed along with it's
  exact results.\n\nFrom there\, we'll peel back the layers to reveal [**ch
 atlas**](https://pypi.org/project/chatlas/)\, the foundation powering quer
 ychat. chatlas provides a unified\, provider-agnostic interface to 19+ LLM
  providers (OpenAI\, Anthropic\, Google\, local models via Ollama\, and mo
 re). You'll learn how chatlas makes it trivial to:\n\n- Build multi-turn c
 onversations with history management\n- Stream responses in real-time for 
 responsive UIs\n- Switch between providers with minimal code changes\n- De
 fine custom tools that let LLMs interact with external systems (safely)\n-
  Extract structured data using Pydantic models\n\nBy the end of this tutor
 ial\, we'll have built two complete apps: a data exploration chatbot (usin
 g querychat with your own data) and a custom AI assistant with tools you d
 efine. You'll leave with practical patterns for constraining LLM behavior\
 , validating outputs\, and building apps that are genuinely useful\, maint
 ainable and production ready.\n\nInstallation Instructions: Go to [dev.wor
 kshop.posit.team](dev.workshop.posit.team) and sign in prior to the worksh
 op. This will ensure you can access the provided computing environment for
  the tutorial. Once logged in\, click "New Session"\, then "Launch". You m
 ay see a blank page for a minute before being directed to a hosted [Positr
 on session](https://positron.posit.co/) (https://positron.posit.co/). If y
 ou run into issues\, or have any questions\, please email carson@posit.co.
DTSTAMP:20260715T021346Z
LOCATION:AI/ML
SUMMARY:Intro to Safe\, Reliable\, and Maintainable AI Apps in Python (Room
  HSEC 3-150) - Carson Sievert
URL:https://pretalx.com/scipy-2026/talk/HFWAYG/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-scipy-2026-39NQ3Y@pretalx.com
DTSTART;TZID=CST:20260717T143500
DTEND;TZID=CST:20260717T150500
DESCRIPTION: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 includin
 g them in the prompt\, grounding responses in real information. But buildi
 ng a good retrieval system involves many steps: reading diverse file forma
 ts\, chunking text at sensible boundaries\, computing embeddings\, and com
 bining search strategies. This talk introduces raghilda\, a Python framewo
 rk that handles the full retrieval pipeline. We'll cover how RAG works\, h
 ow to build a retrieval system with raghilda\, and how to connect it to an
  LLM with a practical example.
DTSTAMP:20260715T021346Z
LOCATION:Memorial Hall
SUMMARY:Retrieval Augmented Generation with Raghilda - Carson Sievert\, Dan
 iel Falbel\, Tomasz Kalinowski
URL:https://pretalx.com/scipy-2026/talk/39NQ3Y/
END:VEVENT
END:VCALENDAR