BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:RAG – združevanje znanja in umetne inteligence | RAG – integr
 ating knowledge and artificial intelligence
DTSTART:20261120T080000Z
DTEND:20261120T150000Z
DTSTAMP:20261109T083500Z
UID:indico-event-3972@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Pavle Boškoski (Faculty of Information Studies)\, R
 obi Pritržnik\, Biljana Mileva Boshkoska\n\nIzvajalec / Course provider:
  Faculty of information studies in Novo mesto (FIŠ)Predavatelji / Instru
 ctors: Biljana Mileva Boshkoska (FIŠ)\, Robi Pritržnik (FIŠ)\, Pavle Bo
 škoski (FIŠ)\nThis intensive course bridges the gap between static Large
  Language Models and dynamic organizational knowledge. Participants will l
 earn how to build Retrieval-Augmented Generation (RAG) systems on high-per
 formance infrastructure. The content covers the entire architecture\, from
  converting private documents into vector embeddings to utilizing framewor
 ks like LangChain. Upon completion\, participants will be equipped to depl
 oy a secure system that provides accurate answers without the risk of mode
 l hallucinations.\nLearning objectives: Participants will gain a thorough 
 understanding of the RAG architecture and its advantages over model fine-t
 uning. Through hands-on work\, they will master the data preparation proce
 ss\, including text chunking strategies for optimal information retrieval.
  They will learn how vector embeddings function and how to select appropri
 ate models for the semantic processing of documents. Participants will gai
 n concrete experience in setting up vector databases for high-speed conten
 t searching and learn to automate workflows using the LangChain framework\
 , including generating responses with precise source citations.\nCourse co
 ntent: The course begins with an introduction to RAG infrastructure and th
 e role of context in enhancing the relevance of AI responses. This is foll
 owed by a module on data pipelines\, covering document cleaning\, chunking
  strategies\, and metadata tagging. The core part of the course focuses on
  working with vector databases (e.g.\, Pinecone\, Chroma) for semantic sea
 rch. In the practical LangChain segment\, participants build chains\, mana
 ge conversational memory\, and optimize search results. We conclude with a
  chapter on security and evaluation\, testing the system's robustness on r
 eal-world business cases.\nLearning outcomes: After the course\, participa
 nts will be able to independently establish a functioning RAG system that 
 processes private company documents in real time. They will acquire the kn
 owledge to choose the optimal technology stack based on the technical and 
 security requirements of their organization. Effective use of the Python l
 anguage will enable seamless integration of models with their own knowledg
 e bases. With the knowledge gained\, participants will reduce operational 
 risks by ensuring factual accuracy and information traceability\, becoming
  qualified to lead digital transformation projects.\n \nSESSION 1: Vecto
 r Embeddings and Knowledge Architecture\n \nWhen: Friday\, November 20\, 
 2026 | 9:00 AM – 1:00 PM (including break)\n \nWhere: Online (Zoom) and
  UNM FIŠ\, Ljubljanska cesta 31a\, 8000 Novo mesto \n \n\n8:30 - 9:00 |
  Onsite registration\n9:00 – 10:30 | From Documents to Vectors: The RAG 
 Foundation Learn how to bridge the gap between static LLMs and dynamic dat
 a. We will cover the conversion of private organizational documents into v
 ector embeddings—the mathematical language of AI knowledge. \n11:00 –
  12:30 | Managing Knowledge: Vector Databases on HPC Explore the managemen
 t of high-speed vector databases. Learn how to store\, index\, and query m
 assive datasets efficiently using the high-performance infrastructure of H
 PC Trdina. \n12:30 - 13:30 | Lunch break\n\n \nSESSION 2: Orchestration 
 and Deployment \nWhen: Friday\, November 20\, 2026 | 1:00 PM – 4:00 PM 
 (including break) \nWhere: Online (Zoom) and UNM FIŠ\, Ljubljanska cesta
  31a\, 8000 Novo mesto \n\n13:30 – 15:00 | LangChain Orchestration and 
 Retrieval Pipelines Master the orchestration of retrieval pipelines using 
 Python frameworks like LangChain. Learn to connect the user’s query with
  the right data to provide context-aware responses. \n15:00 – 16:30 | L
 aunching the Pipeline: Hallucination-Free AI Practical deployment of a fun
 ctional RAG system. Learn to fine-tune the pipeline to eliminate AI halluc
 inations and ensure accurate\, data-backed responses based on specific dat
 asets. \n\n \nWhy attend?\nHands-on experience on a real system: Design 
 and launch a functional RAG pipeline directly on HPC Trdina.\nFree knowled
 ge: Training is part of the SLAIF initiative to enhance digital competenci
 es.\n \n\nhttps://indico.ijs.si/event/3972/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3972/logo-3560331715.png
LOCATION:Online and on premise
URL:https://indico.ijs.si/event/3972/
END:VEVENT
END:VCALENDAR