Sourcerer: the model reads the thrift find, plain code decides the price

Описание и применение

Sourcerer позволяет офлайн‑оценивать цену на вещи из секонд‑хенд, используя локальную модель Gemma и простую арифметику, без подключения к интернету и API‑ключей.

Задача

Resellers need a quick, offline way to determine the maximum price they should pay for a thrifted item, accounting for fees, shipping, supplies, and desired margin, without relying on internet or API keys.

Результат

Sourcerer enables offline, instant pricing for thrift items, reducing decision time and avoiding costly mistakes, with privacy guarantees and no external API calls.

Рабочий процесс

• 1. Photograph or type the item description.
• 2. Local Gemma model (gemma3:4b) reads the image or text.
• 3. Packages/shared calculates eBay fees, shipping, supplies, and desired margin.
• 4. Verdict card displays MAX OFFER, EST. RESALE, and profit.
• 5. User can edit asking price and see instant re‑pricing.
• 6. App logs provider execution and privacy status.

Доказательства

Photograph an item, or type what you see; a local open‑weight model reads it, and plain TypeScript decides the most you should pay — after eBay's fees, shipping, supplies and the margin you actually want.

Источник

No internet, no API keys, no per‑scan cost.

Источник

The app still boots from the service‑worker cache and prices from her own sold history, tagged estimate so it can never pass for a live comp.

Источник

Hardware, for every timing claim in this post: 8-core CPU, 15.4 GB RAM, an NVIDIA GTX 1650 with 3.6 GB of VRAM — enough to hold part of the model, not all of it, so most inference runs on CPU.

Источник