Bank alerts to a day-book, with a local Gemma

说明与用途

一款面向尼日利亚POS运营商的浏览器日记本应用，使用Gemma 3‑1B在本地GPU上提取银行通知中的客户姓名，支持离线运行。

问题

Mama POS needs to record daily cash inflows from bank transfer alerts without manual note‑taking, but the alerts contain customer names in varying formats that code alone cannot reliably parse.

结果

The app correctly extracts 5/5 kinds and 4/5 names from real alerts, and 30/30 kinds and 23/30 names from synthetic alerts. It runs offline after a one‑time 859 MB download and requires a GPU for full functionality.

工作流

• Open the day‑book app in the browser
• Paste the email alert into the input field
• Code extracts time, amount, and kind of money
• Gemma 3‑1B reads the customer name from the alert text
• App displays a row with all extracted data and a status (Landed/Not seen yet/2 payments)
• User reviews flagged rows (reversals, duplicate amounts)
• At end of day, app calculates totals, estimated charges, and generates a WhatsApp text for the business owner
• Data remains in browser storage
• App can run offline after initial model download

证据

She writes each payment in a notebook, and it "takes long".

来源

Gemma found most of them: on the run in the video it found 3 of 3; on an earlier test run it found 2 of 3.

来源

The first load downloads 859 MB once; after that it loads in a few seconds, with no internet (tested with the network off: ready in 6 s).

来源