BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//FYA7P8
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-TST9LF@pretalx.com
DTSTART;TZID=CET:20260416T140000
DTEND;TZID=CET:20260416T143000
DESCRIPTION:Traditional RAG systems struggle to understand holistic connect
 ions in distributed\, constantly changing knowledge sources that character
 ize real-world organizations. While document-based approaches using vector
  embeddings provide basic retrieval\, they fail to capture relationships a
 nd answer complex questions about interconnected information. Graph-based 
 RAG offers a solution\, but existing implementations like Microsoft's Grap
 hRAG explicitly avoid dynamic operations due to complexity\, requiring cos
 tly rebuilds when knowledge changes.\n\nThis talk introduces a production-
 ready dynamic knowledge graph system that supports real-time insertion\, q
 uerying\, and deletion of information. Through practical implementation de
 tails you will learn to build maintainable knowledge graphs that evolve wi
 th data\, handle ambiguous entities and preserve information lineage.
DTSTAMP:20260412T141905Z
LOCATION:Helium [3rd Floor]
SUMMARY:Dynamic Knowledge Graphs - Jakob Leander Müller
URL:https://pretalx.com/pyconde-pydata-2026/talk/TST9LF/
END:VEVENT
END:VCALENDAR