Presenters

• Kim Groome, Information Specialist, University of Calgary Libraries
• Leeanne Morrow, Associate University Librarian, Student Learning and Engagement, University of Calgary Libraries
• Paul Pival, Research Librarian–Data Analytics, University of Calgary Libraries

Description

In 2021 the University of Calgary Libraries implemented a multilingual reference chatbot by leveraging a commercial product that combines a large language model (LLM) with retrieval-augmented generation (RAG) technology. The chatbot is trained on the library’s own web content, including LibGuides, operating hours, and much more. It extended support to students during the fully virtual environment at the height of the pandemic, supplementing existing live chat services. Today the library’s reference chatbot is one of six AI chatbots on campus, operating on separate knowledge bases, answering questions day and night.

In this webinar, presenters from the University of Calgary will share about the genesis, implementation, and lessons learned from the AI reference chatbot, reflecting on the past three years of operation. In particular, they will discuss how the chatbot has deflected 50 percent of questions from the human-managed live chat, freeing 1.5 FTE reference staff to support higher level tasks. Participants will also learn how the Calgary team manages the chatbot, adjusting as conditions change, as well as how the AI chatbot is part of a broader AI strategy in the library.

This webinar will be relevant to anyone interested in how libraries are leveraging AI, particularly in the provision of student support.

All affiliates of OCLC Research Library Partnership organizations are invited to participate.