Hacker News new | ask | show | jobs
by kapitalx 439 days ago
If you're limited to open source models, that's very true. But for larger models and depending on your document needs, we're definitely seeing very high accuracy (95%-99%) for direct to json extraction (no markdown in between step) with our solution at https://doctly.ai.
1 comments

In addition, gemini Pro 2.5 does really well with bounding boxes, but yeah not open source :(