Lucid - AI Notes Platform
FastAPI backend with auth, OCR, PostgreSQL/pgvector retrieval, and AI Q&A over lecture notes.
Lucid is an education-focused platform that turns lecture images and notes into searchable study assets. The backend coordinates user authentication, file storage, OCR, embeddings, PostgreSQL/pgvector retrieval, and AI Q&A so students can organize material and ask questions against their own notes.
Built API workflows for upload, OCR, embeddings, retrieval, and Q&A
Designed authenticated note storage with Supabase and PostgreSQL/pgvector
Added async processing, rate limiting, and backend tests
Impact
One workflow for upload, OCR, semantic search, and study Q&A
Role
Python Backend / AI Engineer
Timeline
2025
Key tags
Problem
Students often accumulate fragmented lecture slides, notes, and screenshots that are difficult to search or study from efficiently.
Solution
Built a backend workflow that accepts lecture images, extracts text with OCR, generates embeddings, stores notes, and enables semantic search and AI-guided study support.
Architecture
A FastAPI backend coordinates OCR, embeddings, background processing, and API workflows. PostgreSQL with pgvector stores retrieval-ready chunks, Supabase handles auth and storage, and Gemini powers question answering.
Challenges
- Processing noisy lecture content and varying slide quality
- Keeping retrieval relevant across mixed academic materials
- Designing AI support that feels useful instead of distracting
Technology stack
Continue exploring
More case studies
Knowledge Graph RAG (ToPWR)
Helps students and staff query university information spread across pages, departments, and systems.
NeuroPark - 3D Vehicle Detection
Supports smart parking analysis by estimating vehicles and scene geometry from regular RGB images.
Medical Chatbot RAG
Provides educational health Q&A from retrieved source content instead of free-form LLM answers.