Implementing Retrieval-Augmented Generation for Academic Libraries
A Technical Case Study using Azure AI
DOI:
https://doi.org/10.23974/ijol.2026.vol11.1.601Abstract
This article details the technical development of a Retrieval-Augmented Generation (RAG) system designed to enhance discovery within an academic library's institutional repository. Conducted during a six-month research leave in 2025, this project explores the practical application of emerging cloud-based AI tools in a library context. We developed a prototype that integrates the University of Manitoba’s MSpace repository with Microsoft Azure AI services. The system utilizes an OAI-PMH harvester to retrieve metadata, generates semantic vector embeddings via the text-embedding-ada-002 model, and indexes these vectors in Azure AI Search. A custom front-end application facilitates both traditional keyword search and generative, context-aware chat interactions. This paper documents the development environment, script logic, and specific technical challenges overcome—such as OAI-PMH pagination errors and API versioning conflicts—providing a reproducible roadmap for libraries seeking to explore semantic search technologies.
Downloads
References
Alshammari, S., Basalelah, L., Walaa Abu Rukbah, Alsuhibani, A., & Wijesinghe, D. S. (2024). PyZoBot: A Platform for Conversational Information Extraction and Synthesis from Curated Zotero Reference Libraries through Advanced Retrieval-Augmented Generation. arXiv.Org. https://doi.org/10.48550/arXiv.2405.07963
Burtsev, M., Reeves, M., & Job, A. (2024). The Working Limitations of Large Language Models. MIT Sloan Management Review, 65(2), 8–10.
Columbia University. (2024, May 24). Enhancing library search system with AI technology at Columbia University. https://etc.cuit.columbia.edu/news/AICoP-library-augment-discovery-with-AI
Finkelstein, J., Moskovitch, R., & Parimbelli, E. (2024). Artificial Intelligence in Medicine: 22nd International Conference, AIME 2024, Salt Lake City, UT, USA, July 9-12, 2024, Proceedings, Part I (2024th edition, Vol. 14844). Springer.
Huang, Y., & Huang, J. (2024). A survey on retrieval-augmented text generation for large language models. arXiv.Org. http://arxiv.org/abs/2404.10981
Kamath, U., Keenan, K., Somers, G., & Sorenson, S. (2024). Large language models : a deep dive : bridging theory and practice (2024th edition). Springer. https://doi.org/10.1007/978-3-031-65647-7
Kaplinsky, P., Singh, R., Fusillo, T. F., Leader, A., Zwicker, J. I., & Mantha, S. (2024). Retrieval augmented generation for the detection of major bleeding events in the electronic health record. Blood, 144(Supplement 1), 2263. https://doi.org/10.1182/blood-2024-203911
Kassorla, M., Georgieva, M., & Papini, A. (2024). AI literacy in teaching and learning: A durable framework for higher education. Educause. https://www.educause.edu/content/2024/ai-literacy-in-teaching-and-learning/introduction
Kautonen, H., & Gasparini, A. A. (2024). B-Wheel – Building AI competences in academic libraries. The Journal of Academic Librarianship, 50(4), Article 102886. https://doi.org/10.1016/j.acalib.2024.102886
Meakin, L. (2024). Exploring the Impact of Generative Artificial Intelligence on Higher Education Students’ Utilization of Library Resources: A Critical Examination. Information Technology and Libraries, 43(3), Article 17246. https://doi.org/10.5860/ital.v43i3.17246
Ni, Z., Qian, Y., Chen, S., Jaulent, M.-C., & Bousquet, C. (2024). Scientific evidence and specific context: leveraging large language models for health fact-checking. Online Information Review, 48(7), 1488–1514. https://doi.org/10.1108/OIR-02-2024-0111
Pride, D., Cancellieri, M., & Knoth, P. (2023). CORE-GPT: Combining open access research and large language models for credible, trustworthy question answering. arXiv.Org http://arxiv.org/abs/2307.04683
Rahman, M. H., & Islam, M. N. (2024). The Impact of ChatGPT for Enhancing Knowledge Management in University Libraries. Journal of Web Librarianship, 18(4), 177–196. https://doi.org/10.1080/19322909.2024.2391907
Toro, S., Anagnostopoulos, A. V., Bello, S., Blumberg, K., Cameron, R., Carmody, L., Diehl, A. D., Dooley, D., Duncan, W., Fey, P., Gaudet, P., Harris, N. L., Joachimiak, M., Kiani, L., Lubiana, T., Munoz-Torres, M. C., O’Neil, S., Osumi-Sutherland, D., Puig, A., … Mungall, C. J. (2024). Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI). arXiv.Org. https://doi.org/10.48550/arxiv.2312.10904
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention Is All You Need. arXiv.Org, https://doi.org/10.48550/arXiv.1706.03762
Wang, C., Ong, J., Wang, C., Ong, H., Cheng, R., & Ong, D. (2024). Potential for GPT Technology to Optimize Future Clinical Decision-Making Using Retrieval-Augmented Generation. Annals of Biomedical Engineering, 52(5), 1115–1118. https://doi.org/10.1007/s10439-023-03327-6
Wheatley, A., & Hervieux, S. (2024). Comparing generative artificial intelligence tools to voice assistants using reference interactions. The Journal of Academic Librarianship, 50(5), Article 102942. https://doi.org/10.1016/j.acalib.2024.102942
Yun, L., Yun, S., & Xue, H. (2024). Improving citizen-government interactions with generative artificial intelligence: Novel human-computer interaction strategies for policy understanding through large language models. PloS One, 19(12), Article e0311410. https://doi.org/10.1371/journal.pone.0311410
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Librarianship
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and the initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the nonexclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
