Header image

TUTORIAL 1: Build Smart Search Interfaces: Use Prompts to Turn Questions into Solr Queries with Minimal Coding

Tracks
Rongomātāne B
Monday, November 3, 2025
9:45 AM - 11:15 AM
Rongomātāne B

Speaker

Agenda Item Image
Miss Pengyin Shan
Senior Research Software Engineer
NCSA/University of Illinois Urbana-Champaign

Build Smart Search Interfaces: Use Prompts to Turn Questions into Solr Queries with Minimal Coding

Summary Abstract

This 1.5-hour tutorial will present a basic workflow for integrating LLM APIs into the document search systems for digital preservation, curation, and discovery applications with LLM prompts and minimal coding. Participants will learn to implement a web interface that transforms users’ natural language questions into structured Solr queries to retrieve relevant documents. The tutorial will be divided into three main sections: Prompt-based web app implementation with Typescript and LLM API integration (60 minutes), followed by web interface optimization strategies to manage API latency (20 minutes). The last 10 minutes will conclude with a discussion of ethical considerations, limitations, and future directions for AI within digital preservation contexts. Participants will leave with practical code samples, implementation strategies, and a deeper understanding of how LLM integration can enhance discovery and access in digital collections.

Biography

Pengyin Shan is a senior research software engineer at the National Center for Supercomputing Applications at the University of Illinois. She possesses extensive library application and full-stack development experience for universities across the US and Canada, and has worked on several projects integrating LLM into data discovery systems.
loading