you have to identify a component before you can look anything up, and the identifying marks are often worn away or facing the wrong direction.
yolov8 handles recognition, llama 3.1 handles the conversation, and the answer is grounded in bharat electronics own manuals rather than invented.
the constraint that shaped it: a confident wrong answer about a defence component is far worse than admitting uncertainty.
how it works
upload a photograph of a component. yolov8 detects what it is, the details come from a structured database, and llama 3.1 turns that into a conversation. flask and mysql underneath. built for bharat electronics at smart india hackathon 2024.
