video1.0<iframe src="https://www.loom.com/embed/fd28447569544670a5b14ce2f3c4e8c0" frameborder="0" width="1092" height="819" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>8191092Loomhttps://www.loom.com8191092https://cdn.loom.com/sessions/thumbnails/fd28447569544670a5b14ce2f3c4e8c0-697fd1e256880e69.gif253.567I developed an AI-powered learning assistant for Elevant Digital designed to support students and internal academic teams by providing instant answers from learning materials. The system is built as a full Retrieval-Augmented Generation (RAG) pipeline and is integrated with Discord for real-time interaction. Project Overview The workflow is designed around two production-grade API endpoints: /ingest endpoint for processing and indexing learning materials /ask endpoint for handling user queries and generating responses System Architecture Learning materials (PDFs) are uploaded via Google Drive A Make.com workflow triggers the ingestion pipeline automatically Documents are processed, chunked, and converted into embeddings Embeddings are stored in Qdrant vector database for semantic search A Discord bot handles student queries in real time Relevant context is retrieved from Qdrant and passed to Gemini AI The model generates accurate, context-aware answers The system is deployed on Render Impact The system enables students to: Ask questions directly from Discord Receive instant explanations from course materials Reduce dependency on immediate teacher availability Access structured academic knowledge in real time