BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.openfest.org//FAB3GR
BEGIN:VTIMEZONE
TZID:EET
BEGIN:STANDARD
DTSTART:20001029T050000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-openfest-2025-FAB3GR@cfp.openfest.org
DTSTART;TZID=EET:20251018T160000
DTEND;TZID=EET:20251018T164000
DESCRIPTION:Large Language Models (LLMs) are powerful\, but they come with 
 a big limitation: their knowledge is frozen at training time and is limite
 d to what was in the training data. Retrieval-Augmented Generation (RAG) c
 hanges that by allowing models to pull in fresh\, domain-specific context 
 at query time.\nIn this talk\, we’ll explore how you can build more inte
 lligent and more useful AI systems by combining LLMs with open-source tool
 s for RAG. We’ll cover:\n- Why “just prompting harder” or having a l
 onger context isn’t enough.\n- The open-source ecosystem: from vector da
 tabases to frameworks.\n- Practical design choices: chunking\, embeddings\
 , retrieval strategies\, and evaluation.\nAt the end of the talk\, you’l
 l have a clear understanding of how to set up your own open-source RAG pip
 eline and make your LLMs not just bigger\, but truly smarter.
DTSTAMP:20260308T131017Z
LOCATION:Hall A
SUMMARY:Make your LLMs smarter with Open Source RAG - Nikolay Stoitsev
URL:https://cfp.openfest.org/openfest-2025/talk/FAB3GR/
END:VEVENT
END:VCALENDAR