The librarian / person recommendation functionality in Primo VE is limited by its need to match query terms literally to the keywords provided for each person. This leads to a very high percentage of Primo queries which could in theory display a suggested librarian but which don't in practice. What if instead those keywords for each librarian were fed into an LLM along with the user's query in order to generate librarian recommendations? This presentation will focus on my proof-of-concept attempts to explore the viability (both cost and otherwise) of this idea.
The librarian / person recommendation functionality in Primo VE is limited by its need to match query terms literally to the keywords provided for each person. This leads to a very high percentage of Primo queries which could in theory display a suggested librarian but which don't in practice. What if instead those keywords for each librarian were fed into an LLM along with the user's query in order to generate librarian recommendations? This presentation will focus on my proof-of-concept attempts to explore the viability (both cost and otherwise) of this idea.
San Diego Ex Libris Knowledge Days and ELUNA Conference 2026 eluna-conf-planning@exlibrisusers.orgTechnical Issues?
If you're experiencing playback problems, try adjusting the quality or refreshing the page.
Questions for Speakers?
Use the Q&A tab to submit questions that may be addressed in follow-up sessions.
