DawaaiDost: a 4B open model that reads doctor shorthand so my grandparents never take the wrong pill
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built 💊 DawaaiDost (दवाई दोस्त) Every week, my 74-year-old grandmother holds up a prescription slip or a medicine blister foil with the exact same confused look: "Beta, yeh Dolo khane ke baad leni thi ya khali pet? Aur yeh BP wali goli subah ki hai ya raat ki?" If you have ever seen an Indian prescription,…
DawaaiDost is an open-source, private medicine guardian designed to help elders never take the wrong pill. This innovative tool addresses the common issue of doctors writing prescriptions in cryptic Latin shorthand, which is difficult for elderly individuals to decipher. Furthermore, the medication blister packs often contain microscopic, faded batch text that the elderly cannot read.
The app tackles these challenges by utilizing a 4B open-weight model, fine-tuned on the Thinking Machines TINKER dataset. This model can read doctor shorthand, voice notes, and even conversational Hinglish notes. It also has an adaptive memory system that learns and remembers corrections, ensuring that the information remains accurate over time.
The app's interface is designed to be empathetic, providing empathetic Hindi voice narration through ElevenLabs. This feature makes it easier for elderly users to understand the instructions without straining their eyes. The app can be accessed either through a browser or on a laptop, providing a seamless user experience.
DawaaiDost was built for the DEV Community Hacktoberfest Weekend Challenge in 2026, focusing on helping friends and family members. With its open-source nature and emphasis on privacy, DawaaiDost offers a reliable solution to the issue of elderly adults taking the wrong medication.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
