Nostalgia Cookbook

Описание и применение

Приложение позволяет пожилым людям сохранять рецепты из голосовых заметок, преобразуя их в структурированные цифровые записи, защищая данные от внешних серверов.

Задача

Grandparents preserve recipes only in memory or disjointed voice memos, making digital archiving difficult.

Результат

The app enables grandparents to digitize recipes while preserving privacy, with structured data extraction and long‑form audio handling.

Рабочий процесс

• Upload or record audio in the app
• Gemini API transcribes audio to raw text
• Local Gemma 2 model extracts recipe structure from transcript
• Structured recipe and narrative are stored in MongoDB Atlas
• User can view and manage archived recipes

Доказательства

I built the Nostalgia Cookbook, a privacy‑first web application designed specifically for my grandparent, who loves cooking but only preserves recipes in their head or via lengthy, disjointed voice memos.

Источник

The application transcribes the audio and uses a hybrid AI system to separate the recipe (ingredients, metric/imperial measurements, structured steps) from the invaluable personal stories, historical context, and anecdotes woven into the recording.

Источник

The application is built using a modern Next.js (App Router) frontend and backend architecture containerized with Docker, backed by MongoDB Atlas for data persistence.

Источник

The raw audio file is initially parsed using the Gemini API (gemini-2.5-flash) via the @google/genai SDK to produce a raw, verbatim stream of consciousness text block from the voice recording.

Источник

This unedited text transcript is then piped locally into Gemma 2 (9B) running on an open-source inference runner (Ollama).

Источник