A RAG system that automatically answers student questions for Teaching Assistants using course content and discourse posts from IIT Madras' Tools in Data Science course.
Project Overview
Virtual Teaching Assistant for IIT Madras' Tools in Data Science course
What We're Building
This project creates a Virtual Teaching Assistant that automatically answers student questions posted on the Discourse forum. It uses a Retrieval Augmented Generation (RAG) system to provide accurate answers based on course content and previous Discourse posts.
Key Components
Data collection from course content and Discourse posts
Text preprocessing and embedding generation
RAG system for answering student questions
FastAPI application with question input and optional file attachments
Vercel deployment configuration
Data Sources
Course content with content for TDS Jan 2025 as on 15 Apr 2025
TDS Discourse posts with content from 1 Jan 2025 - 14 Apr 2025