BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//PYVOBJECT//NONSGML Version 1//EN
BEGIN:VTIMEZONE
TZID:Europe/Brussels
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:20260510T083839Z - 13598@eu441a.odoo.com
DTSTART;TZID=Europe/Brussels:20260511T090000
DTEND;TZID=Europe/Brussels:20260513T130000
CREATED:20260510T083839Z
DESCRIPTION:<a href="https://www.sustain.brussels/event/rag-low-cost-188/re
 gister">RAG Low-Cost </a>\nCourse Description As organisations increasingl
 y rely on large volumes of internal documents\, the ability to build relia
 ble\, cost-effective AI systems for document search and question answering
  has become a key technical capability. This intensive module provides par
 ticipants with a comprehensive\, hands-on understanding of modern document
  processing\, natural language processing\, large language models\, and Re
 trieval-Augmented Generation (RAG) pipelines. The course focuses on applie
 d data science techniques for text and documents\, covering embeddings\, s
 emantic similarity\, vectorisation\, and vector search. Participants will 
 learn how to design and implement a complete RAG pipeline locally\, includ
 ing document ingestion\, chunking strategies\, indexing\, retrieval\, and 
 controlled text generation. Particular attention is given to understanding
  the limitations of large language models\, common sources of hallucinatio
 n\, and the quality-control mechanisms required to produce trustworthy out
 puts. Through a realistic\, compliance-oriented business scenario\, partic
 ipants will build and evaluate a low-cost RAG system tailored to SME needs
 . The module emphasises transparency\, traceability\, and validation\, tea
 ching participants how to enforce source citation\, verify retrieved conte
 nt\, and assess system reliability. Open-source and lightweight local solu
 tions are used throughout to minimise operational and integration costs. B
 y the end of the course\, participants will have designed and deployed a f
 ully functional RAG pipeline\, documented their architectural and design d
 ecisions\, and gained the practical expertise needed to build internal AI-
 powered knowledge systems that are accurate\, auditable\, and fit for real
 -world organisational use. Course Content Day Content 1 Theory: Data Scien
 ce\, NLP\, LLMs\, embeddings\, chunking\, vector databases (FAISS/ChromaDB
 ) 2 Practice: Building a low- [...]
DTSTAMP:20260510T083839Z
LOCATION:BeCentral\, Cantersteen 12\, 1000 Bruxelles\, Belgium
SUMMARY:RAG Low-Cost 
X-ALT-DESC;FMTTYPE=text/html:<a href="https://www.sustain.brussels/event/ra
 g-low-cost-188/register">RAG Low-Cost </a>\nCourse Description As organisa
 tions increasingly rely on large volumes of internal documents\, the abili
 ty to build reliable\, cost-effective AI systems for document search and q
 uestion answering has become a key technical capability. This intensive mo
 dule provides participants with a comprehensive\, hands-on understanding o
 f modern document processing\, natural language processing\, large languag
 e models\, and Retrieval-Augmented Generation (RAG) pipelines. The course 
 focuses on applied data science techniques for text and documents\, coveri
 ng embeddings\, semantic similarity\, vectorisation\, and vector search. P
 articipants will learn how to design and implement a complete RAG pipeline
  locally\, including document ingestion\, chunking strategies\, indexing\,
  retrieval\, and controlled text generation. Particular attention is given
  to understanding the limitations of large language models\, common source
 s of hallucination\, and the quality-control mechanisms required to produc
 e trustworthy outputs. Through a realistic\, compliance-oriented business 
 scenario\, participants will build and evaluate a low-cost RAG system tail
 ored to SME needs. The module emphasises transparency\, traceability\, and
  validation\, teaching participants how to enforce source citation\, verif
 y retrieved content\, and assess system reliability. Open-source and light
 weight local solutions are used throughout to minimise operational and int
 egration costs. By the end of the course\, participants will have designed
  and deployed a fully functional RAG pipeline\, documented their architect
 ural and design decisions\, and gained the practical expertise needed to b
 uild internal AI-powered knowledge systems that are accurate\, auditable\,
  and fit for real-world organisational use. Course Content Day Content 1 T
 heory: Data Science\, NLP\, LLMs\, embeddings\, chunking\, vector database
 s (FAISS/ChromaDB) 2 Practice: Building a low- [...]
END:VEVENT
END:VCALENDAR