A conceptual change in healthcare, personalized medicine uses an individual's genetic profile to forecast disease risk, customize drug treatments, and increase patient outcomes. With its great genomic variety, the development of such systems is hampered in the Indian setting by the scarcity of region-specific, annotated clinical datasets. Using IndiGenome and PharmGKB as main references, this work presents a framework for combining genomic and pharmacogenomic data to enable personalized medicine. A manually built dataset with standardized notations was produced to replicate patient data due to integration difficulties between accessible datasets. This enabled the application of treatment logic and important gene mutations (BRCA1, BRCA2, TP53) based on working artificial intelligence. Future deployment with actual genomic data builds on this Streamlit-based application, which is able to predict treatments and provide health recommendations.