video1.0<iframe src="https://www.loom.com/embed/426d3a029ba342e3842cafc9bcf9f2a5" frameborder="0" width="1280" height="960" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9601280Loomhttps://www.loom.com9601280https://cdn.loom.com/sessions/thumbnails/426d3a029ba342e3842cafc9bcf9f2a5-a0a7c038dd57f024.gif455.566667Hi, I'm Harsh, and in this video, I demonstrate my document verification system developed for the Chetsi AI assignment. The system utilizes OCR and LLM APIs to extract and validate structured data from KYC documents, implementing seven verification methods to ensure accuracy. I faced challenges such as OCR confusion and date formatting variations, which I addressed through robust solutions. The system achieved over 95% accuracy on test data and is production-ready, with all code and documentation available in the GitHub repo. I encourage you to check it out and explore the implementation details.