This presentation explores the comparative performance of traditional information retrieval systems, such as Solr, against emerging Generative AI (GenAI) models like GPT-4 for digital library resource discovery. Using Miami Life newspaper issues (1920s–1940s) as a case study, the team evaluated both approaches based on relevance, efficiency, user engagement, and system complexity. Findings indicate that while Solr offers faster, scalable keyword-based results, LLM-based systems provide superior contextual understanding and conversational interaction. The study recommends a hybrid framework combining Solr and GenAI models to optimize both precision and user experience in digital libraries.
