BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//talk//KHQ3EK
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-KHQ3EK@pretalx.com
DTSTART;TZID=CST:20260714T080000
DTEND;TZID=CST:20260714T120000
DESCRIPTION:Have you ever been frustrated when an LLM generates outdated or
  deprecated code? It's more common than you'd think. LLMs are trained up t
 o a certain point\, but software keeps moving forward. Functions get depre
 cated\, new versions drop\, APIs change\, old patterns get replaced\, and 
 your model has no idea any of it happened.\n\nRAG\, or Retrieval-Augmented
  Generation\, is the fix. Instead of relying solely on what a model learne
 d during training\, RAG lets you supply it with current\, curated informat
 ion at the moment it generates a response.\n\nIn this 4-hour\, hands-on wo
 rkshop\, you'll build a RAG-powered SciPy coding assistant from the ground
  up. Here's what that looks like in practice:\n\n- **RAG Fundamentals**: Y
 ou'll start by getting familiar with the core ideas behind RAG: what embed
 dings are (numerical representations of text that capture meaning)\, how v
 ector similarity works\, and how ChromaDB (a lightweight vector database) 
 stores and retrieves that information.\n\n- **Building the Knowledge Base*
 *: From there\, you'll build the SciPy knowledge base itself. That means s
 craping SciPy's documentation\, chunking it into digestible pieces\, and p
 rocessing it in a way that's aware of code structure\, not just plain text
 .\n\n- **Wiring Up the Pipeline**: Once the knowledge base is ready\, you'
 ll wire up the full pipeline: querying it intelligently\, engineering prom
 pts that produce reliable code\, and integrating with both OpenAI and Olla
 ma (a tool for running models locally) so you're not locked into one provi
 der.\n\n- **Evaluation and Deployment**: Finally\, you'll wrap everything 
 up by evaluating your system using real retrieval and generation metrics\,
  and deploying a Gradio web app\, a simple tool for building interactive U
 Is in Python\, so your assistant is actually usable by people who aren't s
 taring at a Jupyter notebook.\n\nBy the end\, you'll have a working SciPy 
 assistant and\, more importantly\, a solid understanding of every moving p
 art inside it.
DTSTAMP:20260622T110201Z
LOCATION:AI/ML
SUMMARY:Build a SciPy Coding Assistant with RAG - Cynthia Ukawu
URL:https://pretalx.com/scipy-2026/talk/KHQ3EK/
END:VEVENT
END:VCALENDAR