Generative AI for Library Frequently Asked Questions (Sheridan CAAI in collaboration with Oakville Public Library)

Authors

Kunal Bajaj, Sheridan College
Parth Jigneshkumar Patel, Sheridan College

Document Type

Documentation

Publication Date

2024

Keywords

AI, natural language processing, library assistant, chatbot, large language models, retrieval augmented generation(RAG), open source models, vector databases, Meta LlaMa-2 model.

Description

This project involves developing an AI-powered library assistant designed to improve user experience by providing quick and accurate responses to library-related queries. Leveraging advanced Natural Language Processing techniques like Retrieval Augmented Generation(RAG) and open source Large Language Models (LLMs), the assistant offers features such as book search, resource recommendations, and real-time query resolution. It includes a robust API backend using FastAPI. The assistant aims to address 90% of user inquiries, reducing library staff workload while improving response accuracy and efficiency.

Comments

Principal Investigator: Nick Sajadi

Faculty

Faculty of Applied Science & Technology (FAST)

Copyright

© Kunal Bajaj, Parth Jigneshkumar Patel

Terms of Use

Terms of Use for Works posted in SOURCE.

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

SOURCE Citation

Bajaj, Kunal and Patel, Parth Jigneshkumar, "Generative AI for Library Frequently Asked Questions (Sheridan CAAI in collaboration with Oakville Public Library)" (2024). Featured Student Work. 8.
https://source.sheridancollege.ca/student_work_fast_sw/8