My ISP upgraded my gateway to a newer model and let me keep the old one. Instead of tossing it in the e-waste pile, I turned it (plus a decommissioned enterprise appliance from eBay) into a segmented home network with a private Jellyfin media server. It came together over a weekend, and I'm writing it up in case the approach is useful to someone else.

An AMD Ryzen AI Max+ 395 laptop with its integrated Radeon 8060S GPU and unified memory can run open-weight models from 4B parameters up to a 120B mixture-of-experts model, no cloud GPU needed. gpt-oss-120b generates around 35-40 tokens per second, and the 20B and 4B models are faster still. That's enough for the soviet.recipes project: this hardware can host a model large enough to attempt vision-language OCR locally.

The Statement Processor reads PDF bank and credit card statements, extracts every transaction, and groups them by vendor. It's finished and on GitHub under an MIT license. Building it surfaced a problem worth writing down: even on a clean, digitally-generated PDF straight from the bank, the table extraction sometimes dropped a row, usually the last one in a transaction table. A sum check that compares the extracted transactions against the total the statement already prints on itself is what made the output trustworthy.

Two HP ZBook units arrived damaged from shipping in a row: the first had a cracked screen, and its replacement had a screw missing from the cover. Two for two isn't the batting average anyone wants from a laptop. I ordered the ZBook with 128GB of RAM to run local AI inference experiments, and to replace an old laptop that was dying.

Docling already does most of what a batch text-extraction harness does: it iterates over documents, swaps OCR backends, handles per-document errors, and exports structured output. So the code worth writing for the soviet.recipes project is a thin pipeline around Docling that adds the three things Docling leaves to me: image preprocessing before extraction, a neutral slot for engines Docling does not wrap, and consistent scoring across every approach I test. So far I've built the engine slot and the batch loop that drives it; preprocessing and scoring are designed but not written yet.

Docling with the EasyOCR engine extracted the Cyrillic text and page structure from a scanned Soviet cookbook, but it dropped text where the pages curved away from the camera. That data loss makes this configuration insufficient on its own for the soviet.recipes project. I tested four sample pages configured for Russian and English, using Kiro.dev to write the script.