"varahi team on AMD AI League Hackathon"

The AMD Medical RAG & Prescription Scanner is a containerized Retrieval-Augmented Generation system designed and optimized for high-performance clinical data analysis in AMD ROCm environments. Clinical workflows deal with high volumes of unstructured and semi-structured documentation, including complex laboratory diagnostics, patient histories, and handwritten or printed prescription records. Extracting reliable dosages, administration frequencies, and patient metrics requires both domain accuracy and verifiable source grounding. This project addresses those challenges by implementing a decoupled, low-latency client-server architecture. The backend daemon manages document ingestion, structured entity extraction, and vector index generation. Inter-process communication between the lightweight command-line interface and the inference engine is mediated directly via high-speed UNIX domain sockets (/tmp/rag_service.sock), ensuring minimal runtime overhead.