EduQuery: AI-Powered Assistant for University Academic Support
Supervisor : Nafiseh Kahani
Team size: Minimum 3, Maximum 4
| CSE | SE | Comm | Biomed | EE | Aero | Special |
|---|---|---|---|---|---|---|
| Yes | Yes | No | No | No | No | No |
Description
EduQuery is a smart web-based assistant designed to help university students get accurate answers to academic and administrative questions. The system uses a combination of natural language processing and document retrieval techniques to respond to student queries based on official university policies and guidelines. Students can ask questions through a simple web interface or email, and the system will generate relevant answers by retrieving information from a curated knowledge base and using a large language model (LLM) to formulate clear, context-aware responses. This ensures that the assistant delivers not only fluent but also factually grounded replies using retrieval-augmented generation (RAG). To implement this project, students will use tools such as React or Vue for the frontend and Node.js, Django, or Flask for the backend. AI functionality can be built using libraries like LangChain or Haystack for RAG workflows, with vector databases such as FAISS or Chroma for semantic search. Document embeddings may be generated using models from providers like OpenAI, Hugging Face, or Cohere. This project gives students hands-on experience with full-stack development, LLM integration, and AI-driven question answering systems, while also teaching them how to convert real-world policy documents into structured knowledge sources for intelligent applications.
Prerequisites:
Strong programming skills