A receipt sorter that never leaves your laptop (Gemma + Ollama)

说明与用途

Local Receipt Sorter 使用 Gemma 视觉模型在本地处理收据和发票，提取结构化数据，允许用户审核并导出 CSV/Excel，展示小型开源模型可在本地完成隐私敏感任务。

问题

Freelancers need to extract data from receipts and invoices without uploading documents to external services.

结果

On 25 test documents (15 PDFs, 10 photos, 15 screenshots) the tool extracted structured data, flagged anomalies, and allowed user review before export, demonstrating that a small open model can perform receipt parsing locally.

工作流

• Install Ollama and pull gemma3:4b
• Install Python dependencies via pip
• Run Streamlit app
• Drop receipts into the interface
• Model extracts structured data into JSON
• Rule‑based checker flags missing or inconsistent fields
• User reviews and edits data in an editable table
• Export CSV/Excel for accountant

证据

Local Receipt Sorter is a small app that runs entirely on the user’s own computer. You drop in receipts, it reads the vendor, date, invoice number, currency, subtotal, tax and total, flags anything suspicious, and exports a CSV or Excel file for the accountant.

来源

I tested it on 25 documents: 15 PDFs, 10 photos and 15 screenshots.

来源

The documents are read by a model running on the user’s own computer.

来源