I poisoned 20 drug names to find out whether a local model belongs in a pharmacy
说明与用途
该工作流读取手写处方,使用本地 gemma3:4b 模型解释药品名称,应用确定性安全检查,并将不确定行标记给人工审核,从而提高准确性并减少药房的手工工作量。
问题
A neighbourhood medical shop in India needs a reliable way to read handwritten prescriptions and decide which lines can be filled automatically and which require human review, without relying on network connectivity.
结果
The system processes a prescription in ~58 s on an eight‑core laptop, flags all lines for review due to low confidence, and demonstrates that a local LLM can correctly interpret drug names when combined with deterministic safety checks.
工作流
- Photograph handwritten prescription
- Run macOS Vision OCR to extract text
- Send extracted text to local gemma3:4b model via Ollama for drug name interpretation
- Apply deterministic gate checks (safety, grounding, vocabulary)
- Flag lines below confidence threshold or failing checks for human review
- Human reviews flagged lines and completes dispensing
证据
The whole pipeline runs from one command on the shop's machine: python3 scripts/run_page.py prescription.jpg
The OCR reads. The model understands. The gate decides. Only one of those three is allowed to be wrong quietly, and it is not the model.
- 记录日期: 2026-10-17T05:41:25.524Z