BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260504T233820Z
UID:FA4C8E10-D214-4620-A2C9-4607FBB2F7DF
DTSTART;TZID=America/Denver:20260520T180000
DTEND;TZID=America/Denver:20260520T193000
DESCRIPTION:Presentation: Retrieval Augmented Generation (RAG) Pipelines\n\
 nAbstract: Large language models provide powerful capabilities for generat
 ing natural language responses\, but systems built solely on generative mo
 dels often suffer from hallucinations\, outdated knowledge\, and limited d
 omain accuracy. Retrieval Augmented Generation (RAG) addresses these chall
 enges by combining modern information retrieval techniques with generative
  AI models. In a RAG system\, relevant documents are retrieved from extern
 al knowledge sources at query time and provided to the model as contextual
  input\, enabling responses grounded in verifiable information. This talk 
 explains the architecture of RAG pipelines and walks through the stages in
 volved in building them\, including data collection\, document processing\
 , embedding generation\, vector search\, retrieval\, and prompt constructi
 on. Implementation approaches and tooling in both the .NET and Python ecos
 ystems will be discussed\, along with considerations for data curation\, w
 eb scraping\, and responsible engineering practices when building AI syste
 ms. Attendees gain practical skills to build accurate\, production-ready A
 I systems using Retrieval Augmented Generation and real-world tools.\n\nSp
 eaker(s): Scott Swindell\n\nVirtual: https://events.vtools.ieee.org/m/5584
 89
LOCATION:Virtual: https://events.vtools.ieee.org/m/558489
ORGANIZER:gowansj@ieee.org
SEQUENCE:14
SUMMARY:CIR & CIS: Retrieval Augmented Generation (RAG) Pipelines
URL;VALUE=URI:https://events.vtools.ieee.org/m/558489
X-ALT-DESC:Description: <br /><div class="presentation-title"><strong>Prese
 ntation: Retrieval Augmented Generation (RAG) Pipelines</strong></div>\n<d
 iv class="abstract">&nbsp\;</div>\n<div class="abstract"><strong>Abstract:
 </strong> Large language models provide powerful capabilities for generati
 ng natural language responses\, but systems built solely on generative mod
 els often suffer from hallucinations\, outdated knowledge\, and limited do
 main accuracy. Retrieval Augmented Generation (RAG) addresses these challe
 nges by combining modern information retrieval techniques with generative 
 AI models. In a RAG system\, relevant documents are retrieved from externa
 l knowledge sources at query time and provided to the model as contextual 
 input\, enabling responses grounded in verifiable information. This talk e
 xplains the architecture of RAG pipelines and walks through the stages inv
 olved in building them\, including data collection\, document processing\,
  embedding generation\, vector search\, retrieval\, and prompt constructio
 n. Implementation approaches and tooling in both the .NET and Python ecosy
 stems will be discussed\, along with considerations for data curation\, we
 b scraping\, and responsible engineering practices when building AI system
 s. Attendees gain practical skills to build accurate\, production-ready AI
  systems using Retrieval Augmented Generation and real-world tools.</div>
END:VEVENT
END:VCALENDAR