AI Study Assistant Using Vector Database and Large Language Models for Intelligent Question Answering from PDF Documents

The rapid advancement of Artificial Intelligence (AI) and Large Language Models (LLMs) has introduced new possibilities in personalized education and intelligent learning systems. This paper proposes an AI Study Assistant using Vector Database and Large Language Models that enables students to interact with educational documents through intelligent question answering. The proposed system implements a Retrieval-Augmented Generation (RAG) framework, where uploaded PDF documents are processed, converted into semantic embeddings, and stored in a vector database. When a user submits a query, the system retrieves the most relevant document sections using similarity search and provides accurate responses through an integrated Large Language Model. Unlike traditional search-based learning platforms, the proposed approach understands the context of user queries and generates meaningful answers from the provided study materials. The system helps students reduce manual searching time, improve knowledge understanding, and achieve personalized learning experiences.