Smart Library Assistant

Within the domain of Smart Library Assistant, our project aims to enhance the digital library using Retrieval-Augmented Generation. Researchers, students, and theologians often struggle to find precise answers to their questions amid the large volume of Christian literature books. Traditional methods require reading through large texts and archives, such as the Christian Classics Ethereal Library (CCEL), which, unless you know where to look, is a time-consuming process. Existing search tools lack contextual understanding and may return irrelevant results that do not answer the user's question.

Retrieval-augmented generation (RAG) is the main solution used for our approach, aiming to integrate a pre-trained Large Language Model, specifically Claude, with a dataset of Christian texts from CCEL. Instead of relying only on the model's pre-trained knowledge of Christian texts, RAG retrieves relevant paragraphs and their associated metadata directly from our dataset in response to a user's query. To achieve this, the system uses embeddings to identify and retrieve semantically similar passages from the dataset, and these passages are then fed into the Large Language Model as context.

The key features of our system enhance the user experience and the accuracy of the results. First, it offers a domain-specific search, explicitly tailored to our domain and rigorously tested on theological texts to ensure relevance and precision. Second, the system includes citation generation, meaning that responses will include a link to the cited paragraph, therefore adding more confidence that the answers sent to users are accurate. Finally, we will create a user-friendly interface, featuring an intuitive chatbot that automatically applies filters based on user queries and supports follow-up questions for a more natural conversation experience.