BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//compute-paris-2026//talk//37KV87
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251125T000000
TZNAME:CET
TZOFFSETFROM:+0100
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T030000
RDATE:20271031T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Accelerating Vector Search: Finding the needle when the haystack g
 ets bigger and bigger - Mickael Ide
DTSTART;TZID=Europe/Paris:20261125T105000
DTEND;TZID=Europe/Paris:20261125T112000
DTSTAMP:20260930T120937Z
UID:pretalx-compute-paris-2026-37KV87@pretalx.com
DESCRIPTION:In recent years\, the explosion of data sources and data volum
 es available has made their management increasingly difficult for organiza
 tions. Companies are left with vast amounts of unstructured data such as t
 ext documents\, images\, or videos\, which could now be unlocked thanks to
  the availability of high quality embedding models. However\, this data is
  underutilized because its processing would require too much time\, especi
 ally when its size reaches above the billions of records.\nThis talk will 
 guide you through the domain of vector search\, which are techniques that 
 can be used to efficiently index and retrieve huge amounts of unstructured
  data. We will present classical and state of the art algorithms used in t
 he most popular open-source vector search libraries (cuVS\, FAISS\, …)\,
  their tradeoffs\, limitations\, and how GPUs can accelerate those algorit
 hms when the scale of data becomes challenging.\nAdditionally\, we will pr
 esent how those techniques can be applied on Milvus\, an open-source vecto
 r database\, to speed-up indexing workflows on billions of vectors. What u
 sed to take multiple weeks can be reduced to a few days\, while keeping an
  exceptionally low search latency\, suitable for recommendation\, search\,
  and RAG applications that operate over unstructured data embeddings.
LOCATION:Room 108
URL:https://pretalx.com/compute-paris-2026/talk/37KV87/
END:VEVENT
END:VCALENDAR