https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
Ingest Demo: Heterogeneous Documents
Captures screenshots from a mix of URLs, PDFs, and HTML files in one call.
Run
cd pixelrag
uv run python demos/render/run.py
What it does
- Fetches 3 Wikipedia articles (URLs)
- Renders 2 local HTML files (created on the fly)
- Produces tiled JPEG screenshots for all 5
- Shows a summary of tiles, sizes, and timing