BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Springshare//LibCal//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-TIMEZONE:America/New_York
X-PUBLISHED-TTL:PT15M
BEGIN:VEVENT
DTSTART:20260228T140000Z
DTEND:20260228T220000Z
DTSTAMP:20260228T000000Z
SUMMARY:NVIDIA Deep Learning Institute Workshop: Building RAG Agents with LLMs
DESCRIPTION: \n\n\n\n\nBuilding RAG Agents with LLMs\n\nCourse Details\n\n 
 \n\nDuration: 08:00\n\nLevel: Technical - Intermediate\n\nSubject: 
 Generative AI/LLM\n\nLanguage: English\n\nCourse Prerequisites: 
 \n\n\n	\n	Introductory deep learning knowledge\, with comfort with PyTorch 
 and transfer learning preferred.\n	\n	Intermediate Python experience\, 
 including object-oriented programming and libraries.\n\n\nAbout this 
 Course\n\nThe evolution and adoption of large language models (LLMs) have 
 been nothing short of revolutionary\, with retrieval-based systems at the 
 forefront of this technological leap. These models are not just tools for 
 automation\; they are partners in enhancing productivity\, capable of 
 holding informed conversations by interacting with a vast array of tools 
 and documents. This course is designed for those eager to explore the 
 potential of these systems\, focusing on practical deployment and the 
 efficient implementation required to manage the considerable demands of 
 both users and deep learning models. As we delve into the intricacies of 
 LLMs\, participants will gain insights into advanced orchestration 
 techniques that include internal reasoning\, dialog management\, and 
 effective tooling strategies.\n\n\n\nLearning Objectives\n\nThe goal of the 
 course is to teach participants how to:\n\n\n	Compose an LLM system that 
 can interact predictably with a user by leveraging internal and external 
 reasoning components.\n	Design a dialog management and document reasoning 
 system that maintains state and coerces information into structured 
 formats.\n	Leverage embedding models for efficient similarity queries for 
 content retrieval and dialog guardrailing.\n	Implement\, modularize\, and 
 evaluate a RAG agent that can answer questions about the research papers in 
 its dataset without any fine-tuning.\n\n\nBy the end of this workshop\, 
 participants will have a solid understanding of RAG agents and the tools 
 necessary to develop their own LLM applications.\n\n\n\nTopics 
 Covered\n\nThe workshop includes topics such as LLM Inference Interfaces\, 
 Pipeline Design with LangChain\, Gradio\, and LangServe\, Dialog Management 
 with Running States\, Working with Documents\, Embeddings for Semantic 
 Similarity and Guardrailing\, and Vector Stores for RAG Agents. Each of 
 these sections is designed to equip participants with the knowledge and 
 skills necessary to develop and deploy advanced LLM systems 
 effectively.\n\n\n\nCourse Outline\n\n\n	Introduction to the workshop and 
 setting up the environment.\n	Exploration of LLM inference interfaces and 
 microservices.\n	Designing LLM pipelines using LangChain\, Gradio\, and 
 LangServe.\n	Managing dialog states and integrating knowledge 
 extraction.\n	Strategies for working with long-form documents.\n	Utilizing 
 embeddings for semantic similarity and guardrailing.\n	Implementing vector 
 stores for efficient document retrieval.\n	Evaluation\, assessment\, and 
 certification.\n\n\n\n
LOCATION:Research Computing
ORGANIZER;CN="David Reddy":MAILTO:reddydp@mailbox.sc.edu
CATEGORIES:Artificial Intelligence, Research Computing
CONTACT;CN="David Reddy":MAILTO:reddydp@mailbox.sc.edu
STATUS:CONFIRMED
UID:LibCal-16322519
URL:https://libcal.library.sc.edu/event/16322519
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
BEGIN:VALARM
TRIGGER:-PT15M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT

END:VCALENDAR