BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:HPC in Practice IV: Parallel Processing for AI Projects
DTSTART:20261130T080000Z
DTEND:20261130T160000Z
DTSTAMP:20260928T002400Z
UID:indico-event-3825@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Biljana Mileva Boshkoska\, Robi Podtržnik\, Srdjan 
 Šrbić\, Pavle Boškoski\n\nCourse provider: Faculty of Information Studi
 es in Novo mesto (FIŠ)Instructors: Biljana Mileva Boshkoska (FIŠ)\, Srdj
 an Šrbić (FIŠ)\, Robi Podtržnik (FIŠ)\, Pavle Boškoski (FIŠ)\nThis 
 intensive 8-hour course bridges the gap between static Large Language Mode
 ls and dynamic organizational knowledge. Participants will learn how to bu
 ild Retrieval-Augmented Generation (RAG) systems on high-performance infra
 structure. The content covers the entire architecture\, from converting pr
 ivate documents into vector embeddings to utilizing frameworks like LangCh
 ain. Upon completion\, participants will be equipped to deploy a secure sy
 stem that provides accurate answers without the risk of model hallucinatio
 ns.\nLearning objectives: Participants will gain a thorough understanding 
 of the RAG architecture and its advantages over model fine-tuning. Through
  hands-on work\, they will master the data preparation process\, including
  text chunking strategies for optimal information retrieval. They will lea
 rn how vector embeddings function and how to select appropriate models for
  the semantic processing of documents. Participants will gain concrete exp
 erience in setting up vector databases for high-speed content searching an
 d learn to automate workflows using the LangChain framework\, including ge
 nerating responses with precise source citations.\nCourse content: The cou
 rse begins with an introduction to RAG infrastructure and the role of cont
 ext in enhancing the relevance of AI responses. This is followed by a modu
 le 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 search. In the pr
 actical LangChain segment\, participants build chains\, manage conversatio
 nal memory\, and optimize search results. We conclude with a chapter on se
 curity and evaluation\, testing the system's robustness on real-world busi
 ness cases.\nLearning outcomes: After the course\, participants will be ab
 le to independently establish a functioning RAG system that processes priv
 ate company documents in real time. They will acquire the knowledge to cho
 ose the optimal technology stack based on the technical and security requi
 rements of their organization. Effective use of the Python language will e
 nable seamless integration of models with their own knowledge bases. With 
 the knowledge gained\, participants will reduce operational risks by ensur
 ing factual accuracy and information traceability\, becoming qualified to 
 lead digital transformation projects.\n\nhttps://indico.ijs.si/event/3825/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3825/logo-1596601024.png
LOCATION:Slovenija
URL:https://indico.ijs.si/event/3825/
END:VEVENT
END:VCALENDAR