Problem
The challenge
Handwritten study material is hard to search, summarize, and reuse. Students need a grounded way to ask questions over their own notes.
Solution
What I built
I built a RAG assistant that ingests photographed handwritten notes, extracts text with OCR, indexes content with embeddings, and answers questions from retrieved context.
Architecture
How it works
- OCR converts photographed notes into usable text for downstream processing.
- Chunking, embeddings, and vector search keep answers grounded in the user's own notes.
- Question answering, summarization, and study-material generation run from retrieved context.
Implementation
Project highlights
- Built a RAG assistant that turns photographed handwritten notes into a searchable knowledge base.
- Engineered chunking, indexing, and vector retrieval to keep responses grounded.
- Enabled question answering, summarization, and study-material generation for handwritten content.