[
  {
    "id": "1978085097204023577",
    "login": "nanonets",
    "url": "https://x.com/nanonets/status/1978085097204023577",
    "text": "Introducing Nanonets-OCR2: a lightweight 3B VLM ... We have trained the model on close to 3 million documents. It is multi-lingual and can handle handwritten documents. Live demo: docstrange.",
    "source": "google"
  },
  {
    "id": "1954095268497928410",
    "login": "tom_doerr",
    "url": "https://x.com/tom_doerr/status/1954095268497928410",
    "text": "Tom Dörr (@tom_doerr) on X GitHub - NanoNets/docstrange: Extract and convert data from any document, images, pdfs, word doc,... github.com. 0. 0. 12.",
    "source": "google"
  },
  {
    "id": "1951198078083670267",
    "login": "nanonets",
    "url": "https://x.com/nanonets/status/1951198078083670267",
    "text": "Nanonets on X: \"Your LLMs are hungry for data, but documents ... DocStrange is the answer! Our open-source solution turns any document into clean, LLM-ready data with one command. Give your models what they ...",
    "source": "google"
  },
  {
    "id": "2082329772420464970",
    "login": "ai_suxiaole",
    "url": "https://x.com/ai_suxiaole/status/2082329772420464970",
    "text": "给AI 投喂PDF 和图片时，表格提取经常格式错乱，复杂排版 ... ... DocStrange，它专门处理文档到数据的转换能把各种文档精准转成大模型最友好的Markdown 或结构化JSON 支持PDF、图片、Office 文档甚至网页链接核心基于 ...",
    "source": "google"
  }
]