{
  "feed_url": "https://gbilder.com/tags/pdf/feed.json",
  "home_page_url": "https://gbilder.com/tags/pdf/",
  "items": [
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.llamaindex.ai/blog/introducing-extract-v2-5\"\u003ehttps://www.llamaindex.ai/blog/introducing-extract-v2-5\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-10-03T11:31:51+02:00",
      "external_url": "https://www.llamaindex.ai/blog/introducing-extract-v2-5",
      "id": "https://gbilder.com/bookmarks/01M4EHSNX0GPZ9HM40JS14QJE2/",
      "tags": [
        "ml-models",
        "pdf",
        "ocr",
        "entity-extraction"
      ],
      "title": "Introducing Extract v2.5",
      "url": "https://gbilder.com/bookmarks/01M4EHSNX0GPZ9HM40JS14QJE2/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/beatrizalmeidaf/papero-pdf-text-extractor\"\u003ehttps://github.com/beatrizalmeidaf/papero-pdf-text-extractor\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-10-02T21:08:06+02:00",
      "external_url": "https://github.com/beatrizalmeidaf/papero-pdf-text-extractor",
      "id": "https://gbilder.com/bookmarks/01M4EHSNWVR4M7NM67Z24J2YYY/",
      "tags": [
        "pdf",
        "tryme"
      ],
      "title": "GitHub - beatrizalmeidaf/papero-pdf-text-extractor: Fast, open-source PDF text extraction API. Files never stored. · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSNWVR4M7NM67Z24J2YYY/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/ScanTailor-Advanced/scantailor-advanced\"\u003ehttps://github.com/ScanTailor-Advanced/scantailor-advanced\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-30T18:17:48+02:00",
      "external_url": "https://github.com/ScanTailor-Advanced/scantailor-advanced",
      "id": "https://gbilder.com/bookmarks/01M4EHSNVMB5AHQPCDC9TYKGEM/",
      "tags": [
        "pdf"
      ],
      "title": "GitHub - ScanTailor-Advanced/scantailor-advanced: ScanTailor Advanced is the version that merges the features of the ScanTailor Featured and ScanTailor Enhanced versions, brings new ones and fixes. · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSNVMB5AHQPCDC9TYKGEM/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://docs.mistral.ai/studio/search/search-toolkit/ingestion/extractors\"\u003ehttps://docs.mistral.ai/studio/search/search-toolkit/ingestion/extractors\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-30T13:53:38+02:00",
      "external_url": "https://docs.mistral.ai/studio/search/search-toolkit/ingestion/extractors",
      "id": "https://gbilder.com/bookmarks/01M4EHSNVJZXGHKMT1EKKFSSQE/",
      "tags": [
        "pdf",
        "epub"
      ],
      "title": "Document extractors | Mistral Docs",
      "url": "https://gbilder.com/bookmarks/01M4EHSNVJZXGHKMT1EKKFSSQE/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/hug0-l/mistral-ocr-epub-skill\"\u003ehttps://github.com/hug0-l/mistral-ocr-epub-skill\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-30T13:50:53+02:00",
      "external_url": "https://github.com/hug0-l/mistral-ocr-epub-skill",
      "id": "https://gbilder.com/bookmarks/01M4EHSNVGANJ7E2APMBSF8WJ8/",
      "tags": [
        "pdf",
        "epub"
      ],
      "title": "GitHub - hug0-l/mistral-ocr-epub-skill: OCR scanned books to EPUB using Mistral OCR API. Universal — no book-specific rules. · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSNVGANJ7E2APMBSF8WJ8/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/averageclub860/pdf-to-epub-ai\"\u003ehttps://github.com/averageclub860/pdf-to-epub-ai\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-30T13:37:23+02:00",
      "external_url": "https://github.com/averageclub860/pdf-to-epub-ai",
      "id": "https://gbilder.com/bookmarks/01M4EHSNVFC0M4KQVTGW2X8D43/",
      "tags": [
        "pdf",
        "epub"
      ],
      "title": "GitHub - averageclub860/pdf-to-epub-ai: Python scripts pipeline for converting PDF files to clean, readable text format using openai api for post-OCR correction and text refinement. · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSNVFC0M4KQVTGW2X8D43/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/LourensT/PDFtoEPUB\"\u003ehttps://github.com/LourensT/PDFtoEPUB\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-30T13:36:44+02:00",
      "external_url": "https://github.com/LourensT/PDFtoEPUB",
      "id": "https://gbilder.com/bookmarks/01M4EHSNVDE1YCRT0NV18WMNPN/",
      "tags": [
        "pdf",
        "epub"
      ],
      "title": "GitHub - LourensT/PDFtoEPUB · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSNVDE1YCRT0NV18WMNPN/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.llamaindex.ai/blog?tag=LiteParse\"\u003ehttps://www.llamaindex.ai/blog?tag=LiteParse\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-06-20T18:21:13+02:00",
      "external_url": "https://www.llamaindex.ai/blog?tag=LiteParse",
      "id": "https://gbilder.com/bookmarks/01M4EHSM908F5J8SBFE6N38WZB/",
      "tags": [
        "pdf"
      ],
      "title": "Blog",
      "url": "https://gbilder.com/bookmarks/01M4EHSM908F5J8SBFE6N38WZB/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://askubuntu.com/questions/1259632/convert-pdf-to-word-using-libreoffice-in-terminal\"\u003ehttps://askubuntu.com/questions/1259632/convert-pdf-to-word-using-libreoffice-in-terminal\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-06-16T18:43:16+02:00",
      "external_url": "https://askubuntu.com/questions/1259632/convert-pdf-to-word-using-libreoffice-in-terminal",
      "id": "https://gbilder.com/bookmarks/01M4EHSM6AZA32VEK857XWNCTX/",
      "tags": [
        "pdf"
      ],
      "title": "command line - Convert PDF to Word Using Libreoffice in terminal - Ask Ubuntu",
      "url": "https://gbilder.com/bookmarks/01M4EHSM6AZA32VEK857XWNCTX/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://sgaud.com/texts/pdf\"\u003ehttps://sgaud.com/texts/pdf\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-06-12T20:39:12+02:00",
      "external_url": "https://sgaud.com/texts/pdf",
      "id": "https://gbilder.com/bookmarks/01M4EHSM5AZQ4RZ3C5TYN9QDQH/",
      "tags": [
        "pdf"
      ],
      "title": "Adaptive PDFs | Sarthak Gaud",
      "url": "https://gbilder.com/bookmarks/01M4EHSM5AZQ4RZ3C5TYN9QDQH/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.extend.ai/ui\"\u003ehttps://www.extend.ai/ui\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-06-10T21:56:52+02:00",
      "external_url": "https://www.extend.ai/ui",
      "id": "https://gbilder.com/bookmarks/01M4EHSM4F8JKQMZW5Z3442NJ8/",
      "tags": [
        "vraix",
        "ui",
        "pdf"
      ],
      "title": "Open source UI kit for modern document apps - Extend UI",
      "url": "https://gbilder.com/bookmarks/01M4EHSM4F8JKQMZW5Z3442NJ8/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://mathnet.mit.edu/index.html#pipeline\"\u003ehttps://mathnet.mit.edu/index.html#pipeline\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-04-24T18:28:40+02:00",
      "external_url": "https://mathnet.mit.edu/index.html#pipeline",
      "id": "https://gbilder.com/bookmarks/01M4EHSKMFVZGSM5VS8F9RWJPH/",
      "tags": [
        "ocr",
        "mitp",
        "pdf"
      ],
      "title": "MathNet — Explore 30,000+ Olympiad Math Problems",
      "url": "https://gbilder.com/bookmarks/01M4EHSKMFVZGSM5VS8F9RWJPH/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://developers.llamaindex.ai/liteparse/guides/visual-citations/\"\u003ehttps://developers.llamaindex.ai/liteparse/guides/visual-citations/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-04-24T05:54:29+02:00",
      "external_url": "https://developers.llamaindex.ai/liteparse/guides/visual-citations/",
      "id": "https://gbilder.com/bookmarks/01M4EHSKM250BH4N7PWM9VGXR5/",
      "tags": [
        "pdf",
        "tryme"
      ],
      "title": "Visual Citations with Bounding Boxes | LlamaIndex OSS Documentation",
      "url": "https://gbilder.com/bookmarks/01M4EHSKM250BH4N7PWM9VGXR5/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://simonwillison.net/2026/Apr/23/liteparse-for-the-web/#atom-everything\"\u003ehttps://simonwillison.net/2026/Apr/23/liteparse-for-the-web/#atom-everything\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-04-24T05:53:19+02:00",
      "external_url": "https://simonwillison.net/2026/Apr/23/liteparse-for-the-web/#atom-everything",
      "id": "https://gbilder.com/bookmarks/01M4EHSKM0C8Y37WDH58G69GPS/",
      "tags": [
        "pdf",
        "tryme",
        "vraix"
      ],
      "title": "Extract PDF text in your browser with LiteParse for the web",
      "url": "https://gbilder.com/bookmarks/01M4EHSKM0C8Y37WDH58G69GPS/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/run-llama/liteparse\"\u003ehttps://github.com/run-llama/liteparse\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-03-26T22:22:47+02:00",
      "external_url": "https://github.com/run-llama/liteparse",
      "id": "https://gbilder.com/bookmarks/01M4EHSK947FZCVD9B0G0FQ0NS/",
      "tags": [
        "pdf",
        "vraix"
      ],
      "title": "GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSK947FZCVD9B0G0FQ0NS/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/Lulzx/zpdf\"\u003ehttps://github.com/Lulzx/zpdf\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-12-31T00:14:41+02:00",
      "external_url": "https://github.com/Lulzx/zpdf",
      "id": "https://gbilder.com/bookmarks/01M4EHSJ63QY19B7QQMHKQ84EH/",
      "tags": [
        "pdf"
      ],
      "title": "Lulzx/zpdf: Zero-copy PDF text extraction library written in Zig. High-performance, memory-mapped parsing with SIMD acceleration.",
      "url": "https://gbilder.com/bookmarks/01M4EHSJ63QY19B7QQMHKQ84EH/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://bentopdf.com/?ref=selfh.st%22\"\u003ehttps://bentopdf.com/?ref=selfh.st%22\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-12-10T19:58:39+02:00",
      "external_url": "https://bentopdf.com/?ref=selfh.st%22",
      "id": "https://gbilder.com/bookmarks/01M4EHSHXY8CDZRP4KG3X07JK2/",
      "tags": [
        "pdf",
        "tryme"
      ],
      "title": "BentoPDF - The Privacy First PDF Toolkit",
      "url": "https://gbilder.com/bookmarks/01M4EHSHXY8CDZRP4KG3X07JK2/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/plutoprint/plutobook\"\u003ehttps://github.com/plutoprint/plutobook\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-08-21T07:33:02+02:00",
      "external_url": "https://github.com/plutoprint/plutobook",
      "id": "https://gbilder.com/bookmarks/01M4EHSG5C79RARKC4BZKT0CB9/",
      "tags": [
        "ebooks",
        "pdf",
        "python"
      ],
      "title": "plutoprint/plutobook: Paged HTML Rendering Library",
      "url": "https://gbilder.com/bookmarks/01M4EHSG5C79RARKC4BZKT0CB9/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://eliot-jones.com/2025/8/pdf-parsing-xref\"\u003ehttps://eliot-jones.com/2025/8/pdf-parsing-xref\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-08-04T06:44:31+02:00",
      "external_url": "https://eliot-jones.com/2025/8/pdf-parsing-xref",
      "id": "https://gbilder.com/bookmarks/01M4EHSFS2NFCX1QQS0ARZ9SEC/",
      "tags": [
        "pdf"
      ],
      "title": "So you want to parse a PDF? - Eliot Jones",
      "url": "https://gbilder.com/bookmarks/01M4EHSFS2NFCX1QQS0ARZ9SEC/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/Goldziher/kreuzberg\"\u003ehttps://github.com/Goldziher/kreuzberg\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-02-15T13:22:54+02:00",
      "external_url": "https://github.com/Goldziher/kreuzberg",
      "id": "https://gbilder.com/bookmarks/01M4EHSCR9YNT8RHHJGVSG4STM/",
      "tags": [
        "text",
        "pdf",
        "python",
        "tryme"
      ],
      "title": "GitHub - Goldziher/kreuzberg: A text extraction library supporting PDFs, images, office documents and more",
      "url": "https://gbilder.com/bookmarks/01M4EHSCR9YNT8RHHJGVSG4STM/"
    }
  ],
  "language": "en",
  "title": "#pdf · Louche Cannon",
  "version": "https://jsonfeed.org/version/1.1"
}