LumenSeed AI
won 1st prize at Techfest IIT Bombay Medibot challenge for a vector-retrieval RAG translator explaining medical reports.
whenever you get a medical report back from a lab, it is written entirely in dense jargon meant for doctors. if you try to search for the terms online, you usually end up reading extreme diagnosis threads and panicking. most patients have no idea what their own health data means, which is a massive communication gap. we built lumenseed to translate medical reports into clear, friendly language that anyone can read. it doesn't give medical advice—it just explains what the terms mean, what the normal ranges are, and what questions you should actually ask your doctor during your next visit. we built the prototype for the Techfest IIT Bombay Medibot challenge and won first place. we used LangChain to set up a retrieval-augmented generation (RAG) pipeline. when a patient uploads a PDF report, we extract the text, chunk it, and pull reference definitions from verified medical dictionaries stored in a vector database. then, we use a fine-tuned LLM to write the summary, enforcing a strict tone check so it sounds human and calming, not robotic or alarmist. medical data is incredibly sensitive, so we designed the system to run on local-first principles wherever possible, stripping out personally identifiable information (PII) before any text gets processed by the inference layer.