BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//speaker//FTZPWC
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-2025-SFDRTR@pretalx.com
DTSTART;TZID=CET:20250425T132000
DTEND;TZID=CET:20250425T135000
DESCRIPTION:Vector databases are everywhere\, powering LLMs. But indexing e
 mbeddings\, especially multivector embeddings like ColPali and Colbert\, a
 t a bulk is memory intensive. Vector streaming solves this problem by para
 llelizing the tasks of parsing\, chunking\, and embedding generation and i
 ndexing it continuously chunk by chunk instead of bulk. This not only incr
 ease the speed but also makes the whole task more optimized and memory eff
 icient.\n\nThe library gives many vector database supports\, like Pinecone
 \, Weavaite\, and Elastic.
DTSTAMP:20260721T172625Z
LOCATION:Hassium
SUMMARY:Vector Streaming: The Memory Efficient Indexing for Vector Database
 s - Sonam Pankaj\, Akshay Ballal
URL:https://pretalx.com/pyconde-pydata-2025/talk/SFDRTR/
END:VEVENT
END:VCALENDAR