NanoNets releases docext toolkit and 3B vision model for docs
tom_doerr · x · 2026-08-17
NanoNets released docext, an on-premises document intelligence toolkit that converts documents to markdown and detects signatures and watermarks. They also released Nanonets-OCR-s, a 3B parameter model specifically trained for image-to-markdown conversion with semantic understanding of images, signatures, and watermarks.
More from Infra
- IBM Open Sources Docling-Graph: Converting PDFs to Knowledge Graphs — aigleeson · 2026-08-17
- Open-source ETL Duckle loads 20M rows in 15.69s, beats Airbyte — JafarNajafov · 2026-08-17
- How to choose an LLM API? Developers weigh cost, speed, and reliability — Puzzleheaded-Fig1589 · 2026-08-17
- llama.cpp Adds Support for Ling 3.0 Models — parepeg · 2026-08-17
- Open-source zxLLM predicts LLM VRAM usage & KV-cache needs with high precision — Capable_Item_5918 · 2026-08-17
- Fix Qwen3.8-27b Overthinking with Reasoning Budget Flags — MikeNonect · 2026-08-17