Interactive document parsing demo

One document. Four OCR profiles.

Our parsing pipeline using different OCR models. Each output identifies its OCR model; generated visual descriptions are labeled Gemma.

70-page evaluation · ranking and metrics ↗

Inspect evaluation references · source pages + annotations ↗

Saved results · no live inference
PDF + parsed output Page navigation keeps both panes in sync.
View settings
Run details & metrics

NVIDIA GeForce GTX 1660 Ti · 6 GB VRAM. Visual enrichment uses remote Ollama Cloud.

Accepted pages—Full saved selection; not just demo excerpts
Median page time—
GPU memory—
This page—
Timing and memory scopes differ across backends.

Source PDF
Rendered source PDF page
Parsed output

What these measurements establish