BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//scipy-2026//speaker//9TQTHL
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-NWPPHA@pretalx.com
DTSTART;TZID=CST:20260714T133000
DTEND;TZID=CST:20260714T173000
DESCRIPTION:The quality of the retrieval component is what drives Retrieval
 -Augmented Generation (RAG) systems. Therefore\, a well-structured\, measu
 rable\,  and robust retrieval pipeline is critical to building effective l
 arge language model (LLM) applications.\n\nWorking through guided code exa
 mples and hands-on experimentation\, attendees will collectively develop\,
  optimize\,  and enhance the performance of a complete RAG pipeline by imp
 roving retrieval in three stages: _Pre-Retrieval_\, _Mid-Retrieval_\, and 
 _Post-Retrieval_. We will also cover structured and multimodal document pa
 rsing with _Docling_\, systematic evaluation with _RAGAS_\, and a capstone
  _Agentic RAG_ demo using _LangGraph_. The toolkit integrates _Qdrant_ for
  vector search and the _LangChain_ ecosystem for orchestration and experim
 entation.\n\nDuring the hands-on session\, attendees will use Jupyter note
 books to learn about\, experiment with\,  and benchmark techniques that pr
 oduce significant improvements to retrieval quality using production-ready
  open-source libraries. At the end of the session\, each participant will 
 be equipped with a reusable _“Retrieval Playground”_ framework that ca
 n be leveraged to design\, evaluate\,   and continuously improve RAG syste
 ms across various application domains.\n\nInstallation Instructions: https
 ://github.com/mahimaarora/retrieval-playground/tree/main/setup-guides
DTSTAMP:20260715T021347Z
LOCATION:AI/ML
SUMMARY:Engineering Better Retrieval for RAG (Room HSEC 3-110) - Mahima Aro
 ra\, Aarti Jha
URL:https://pretalx.com/scipy-2026/talk/NWPPHA/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-scipy-2026-SEYACQ@pretalx.com
DTSTART;TZID=CST:20260715T152500
DTEND;TZID=CST:20260715T155500
DESCRIPTION:Scientific breakthroughs don’t happen in plain text\, they li
 ve inside multi-column research papers\, dense data tables\, and intricate
  simulation diagrams. Yet the moment standard AI and Retrieval-Augmented G
 eneration (RAG) pipelines encounter these layouts\, they fail. Tables are 
 flattened into meaningless strings. Figures are ignored. The structural si
 gnals that drive scientific reasoning disappear.\n\nIn this talk\, we show
  how to rescue scientific knowledge from the “text-flattening” trap us
 ing _Docling_\, an open-source document understanding library designed to 
 preserve layout\, hierarchy\, and element boundaries. Instead of reducing 
 everything to text\, we treat tables\, figures\, and sections as first-cla
 ss data structures. Attendees will experience a live demo of a realistic s
 cientific R&D workflow: uploading multiple dense technical PDFs\, executin
 g cross-document natural language queries\, and successfully retrieving sy
 nthesized insights from text\, structured tables\, and scientific images
DTSTAMP:20260715T021347Z
LOCATION:Memorial Hall
SUMMARY:Docling for Multimodal Retrieval - Mahima Arora\, Aarti Jha
URL:https://pretalx.com/scipy-2026/talk/SEYACQ/
END:VEVENT
END:VCALENDAR