Dev wires r-1 to Jev for real-time PDF Q&A with on-page highlighting, no embeddings
iamrobotbear · x · 2026-09-23
A developer demoed a document QA combo: parse a PDF once with r-1 to get text, layout, and element positions, then let Jev find relevant bits and highlight them on the page in real time as you ask questions.
The core idea is 'parse once, keep asking': no embeddings to generate, no search index to maintain — the structured layout from parsing doubles as the retrieval layer. A lightweight alternative for cases where you need to know exactly where an answer sits on the page.
More from coding & agent
- Vercel CEO Backs px0, a Lightweight IDE Built for Reviewing Agent-Written Code — arpit_bhayani · 2026-09-23
- Matt Pocock: Stop chasing model releases, improve your agent's harness instead — mattpocockuk · 2026-09-23
- Uncle Bob: AI changes nothing—complexity, not tooling, still makes software slow — blaizedsouza · 2026-09-23
- GBrain: plug your own memory, tools, and skills into any AI — garrytan · 2026-09-23
- Podcast: building a playable game with $8 of parts and AI assistance — aishashok14 · 2026-09-23
- Agent kept searching but never opened the source: four runs expose a hidden failure mode — memokris · 2026-09-23