BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2024//speaker//PVSNU
 G
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-europython-2024-A3E3XE@programme.europython.eu
DTSTART;TZID=CET:20240710T130000
DTEND;TZID=CET:20240710T140000
DESCRIPTION:Retrieval-Augmented Generation (RAG) presents an excellent appr
 oach to overcoming the limitations associated with Large Language Models (
 LLMs)\, such as hallucinations or issues related to the recency of their t
 raining data. However\, relying solely on RAG is insufficient\, particular
 ly when dealing with domain-specific data or verifying a response's adequa
 cy. Neglecting these scenarios can cost time\, money\, and customer satisf
 action. That’s why\, as you develop an application\, it's crucial to eva
 luate your retrieval process\, improve it with advanced techniques if nece
 ssary\, and consider all edge cases\, including handling out-of-domain que
 ries\, and implement fallback mechanisms. Thus\, you ensure that your syst
 em is both resilient and flexible.\nThis poster will explain some problems
  you may encounter in real life and which steps to take to build reliable 
 and resilient RAG applications with the open source LLM framework Haystack
  that you can safely use in production
DTSTAMP:20260513T153353Z
LOCATION:Main Hall A
SUMMARY:Building End-to-End Reliable RAG Applications - Bilge Yücel
URL:https://programme.europython.eu/europython-2024/talk/A3E3XE/
END:VEVENT
END:VCALENDAR