ReplyShelf: an open model finds the reply you already wrote

Описание и применение

ReplyShelf – браузерное приложение, использующее открытый модельный вес для поиска ранее написанных ответов на похожие вопросы поддержки, позволяющее агентам быстро находить и копировать проверенные ответы.

Задача

Support agents often need to reuse previously written replies for paraphrased questions, but finding the right reply becomes a separate task.

Результат

The demo achieved 6 out of 8 correct matches on synthetic paraphrases, with semantic similarity outperforming simple Jaccard overlap in ambiguous cases. The app runs locally in a browser, requiring ~46 MB of assets and a modern WebAssembly‑capable browser.

Рабочий процесс

• Store a reviewed question‑answer card in the shelf
• Ask a new question in the app
• The model computes a semantic similarity score between the new question and all stored questions
• If the highest score exceeds 0.42, the app displays the corresponding saved reply and its source question
• If the top two scores differ by less than 0.06, the app flags ambiguity and shows alternatives
• If no score exceeds 0.42, the app withholds a ready‑to‑copy reply
• Agent reviews the displayed reply, copies it, and personalises it for the customer
• Agent can add new cards, export a JSON backup, or run a local comparison in the "Behind the shelf" view

Доказательства

ReplyShelf gives those answers a second life.

Источник

The core is Xenova/all-MiniLM-L6-v2, an Apache-2.0 open-weight sentence embedding model, running through Transformers.js 3.8.1 and ONNX Runtime’s WebAssembly backend in a Web Worker.

Источник

I tested eight fixed synthetic paraphrases against the same eight-card shelf and compared the model with simple Jaccard word overlap. Both methods retrieved the expected top card 6 out of 8 times.

Источник

The app withholds a ready-to-copy answer because the shelf has no close match.

Источник