Long Notice? Take It Slow. 🦥 Building NoticeNap with Open-Weight AI

Описание и применение

NoticeNap преобразует длинные PDF‑уведомления в структурированный обзор и чек‑лист, сокращая время поиска ключевой информации.

Задача

Applicants struggle to locate deadlines, eligibility, fees, and instructions scattered across long PDF notices, wasting time searching manually.

Результат

NoticeNap transforms a complex PDF notice into a concise, structured summary and actionable checklist, reducing manual search time and improving workflow efficiency.

Рабочий процесс

• Upload PDF
• Extract text page‑by‑page with PyMuPDF
• Send extracted text to local Gemma 2 via Ollama
• Generate structured output (deadlines, eligibility, fees, etc.)
• Validate output with Pydantic, marking missing info as "Not found" or "Needs verification"
• Create action checklist and export to Markdown/iCalendar
• Allow user to review source references and track progress

Доказательства

NoticeNap is a local‑first AI assistant designed to make reading long, information‑heavy PDF notices less tedious.

Источник

NoticeNap combines PDF text extraction, a Python backend, and an open‑weight language model served locally through Ollama.

Источник

The backend uses Pydantic to validate structured data returned through the analysis workflow.

Источник

NoticeNap organizes findings into a checklist, supports tracking task progress, and provides Markdown and calendar export functionality where implemented.

Источник