dubbid

The idea is to also generally handle scanned documents as well. Besides sometimes text boxes can get very distorted with whitespace such that the boxes look to a computer very different then they do in new life.

In practice, you are right that this would be more efficient in many cases (not scanned, no weird whitespace), but in practice, the cost of OCR is so low compared to the LLM costs and the relative consistency of OCR outputs helps a lot means that I don't try to handle the PDF object extraction.

Not quite! This goes one step further to serialize the text for complex layouts in a sensible manner, using a geometry-based approach as specified in the blog post :)

An optical-character-recognition- and computer vision-based approach, better then anything else commercially or open-source available.

Test your smarts against an LLM with our new game! Convince AI cop, steal 10M safe combo, get Ferrari thief to confess, and more! Test your smarts against an LLM with our new game! Convince AI cop, steal 10M safe combo, get Ferrari thief to confess, and more!

See if you can get an LLM, Frank, to give you the combination to its safe.