ABOUT EVENT

Description

This workshop centers on the design and optimization of Retrieval-Augmented Generation (RAG) systems for building responsive, domain-specific search and question-answering applications. Participants will explore how to improve retrieval pipelines through techniques such as reranking, hypothetical document expansion (HyDE), chunking strategies with overlap, vector representation tuning, and small-to-big retrieval methods.

The session will highlight current trends in RAG development and provide practical guidance on how to adapt these systems to different types of data and user needs. Using a hands-on framework deployed on Jetstream infrastructure, attendees will scrape structured content from PDFs and build their own searchable applications—gaining experience with indexing, retrieval, evaluation, and deployment of high-performance, context-aware systems.

Prerequisites

• Have a basic understanding of Github, Python, Jupyter Notebooks
• Watch the suggested video: https://www.youtube.com/watch?v=5Y3a61o0jFQ

Learning objectives

Think critically about building a RAG system for different use cases. Participants can expect to gain an introduction to document extraction (scraping data from a website and a PDF document), set up a ready-to-use Github repo for RAG, test search queries, chunk embed and index data, implement and evaluate retrieval pipelines, evaluate the RAG system and test it with a LLM, and analyze and tune for performance.

Tools Used for this workshop

• Github
• Python
• Jupyter Notebooks
• git

Workshop Instructor

Dr. Roderick Tabalba is a full-stack software developer at the University of Hawai‘i’s Information Technology Services Research Cyberinfrastructure team and an AI engineer at ScienceDocs, where he builds intelligent web-based chatbot applications powered by retrieval-augmented generation (RAG).

Dr. Tabalba earned his PhD from the University of Hawai‘i at Mānoa, where his research focused on voice-driven data visualization and natural user interfaces for data exploration. His work bridges human-computer interaction and AI, with an emphasis on making complex systems easier to use through natural language.

In this workshop, Dr. Tabalba will guide participants through the inner workings of large language models, embeddings, and RAG systems. Attendees will gain hands-on experience deploying intelligent search applications using real-world data on Jetstream cloud infrastructure.