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.

Original post →

More from coding & agent

coding & agent channel →