A RAG-Based AI Chatbot for Dynamic Contextual Question Answering on Educational Platforms

This paper presents a Retrieval-Augmented Generation (RAG)-based AI chatbot designed to provide accurate, context-aware responses to natural language queries on educational websites. The proposed system targets PreGrad.in, a dynamic learning platform, and integrates web content retrieval, semantic embedding, and large language model (LLM) generation. Live content is collected and semantically indexed using Google Gemini text-embedding-004, stored in a FAISS vector database, and queried using LangChain's RetrievalQA framework. The response generation leverages the Gemini-2.0-flash LLM, ensuring fluent, grounded answers. Evaluation demonstrates the system’s ability to handle diverse and dynamic content queries efficiently. This research highlights the potential of RAG pipelines for scalable, domain-specific conversational agents in education and beyond.