In an academic environment, where most of the data related to day-to-day tasks like the timetable, examination duty is either maintained in paper format or in tabular format. Enquires on such data lead to a time-consuming search. The paper addresses to solve one such issue that enquires on faculty availability and other questions related to faculty expertise. The facility is made available through a proposed app known as Faculty Infobot, which is designed to integrate conversational natural language processing with the structured data. Storing and retrieving data in a structured format is best provided queries are in the database-related format. The study analyzes the challenges faced by chatbots in interacting with structured data. Initial study was conducted on a CSV sheet that maintained a timetable; the data was then transformed into embeddings for semantic search. Using the FAISS library, faculty similarity was done. However, as the data grew, search speed reduced, and hence the next study was done on SQLite as it is lightweight. Due to its indexing features, fetching and converting data to equivalent text was comparatively easier. When utilizing SQLite, experimental testing with automated validation and synthetic question-answer pairs showed an 88% increase in correctness and reliability. The combination of Flask web framework, Werkzeug’s secure password hashing, NLP, and SQLite’s efficient data management enabled rapid development, seamless user authentication, and reliable query processing, establishing a scalable blueprint for academic digital assistants.