31–35 of 35 posts
One persistent challenge was generalizing across “wild” PDFs, especially multi-page tables.
Your mention of agentic OCR correction and semantic chunking really caught my attention. I’m curious — how did you architect those to stay consistent across diverse layouts without relying on massive rule sets?
Other players: 1. Trellis (YC W24) 2. Roe AI (YC W24) 3. Omni AI (YC W24) 4. Reductor (YC W24) Other players(extended): 1. Unstract: Open-source ETL for documents ( https://github.com/Zipstack/unstract ) 2. Datalab: Makers of Surya/Marker 3. Unstructured.io
Other players: 1. Trellis (YC W24) 2. Roe AI (YC W24) 3. Omni AI (YC W24) 4. Reductor (YC W24) Other players(extended): 1. Unstract: Open-source ETL for documents ( https://github.com/Zipstack/unstract ) 2. Datalab: Makers of Surya/Marker 3. Unstructured.io
You forgot Nanonets and it even has its own open source model on huggingface.
And hosted model: https://docstrange.nanonets.com/
Earlier quoted context omitted.
You forgot Nanonets and it even has its own open source model on huggingface.
Here is link to open source model: https://huggingface.co/nanonets/Nanonets-OCR-s And hosted model: https://docstrange.nanonets.com/
Earlier quoted context omitted.
Here is link to open source model: https://huggingface.co/nanonets/Nanonets-OCR-s And hosted model: https://docstrange.nanonets.com/
What service do you use to get notifications about nanonets mentions on HN?