{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiamal7kn5agswcudjd545aru3ekqrkskmheqdnrjt3tka3xcnhzdy",
"uri": "at://did:plc:nfto3lv2rcs5s7h7digotzlu/app.bsky.feed.post/3mljirh6r4ma2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreig7saeenw6c3prrms24e2bpcmq7mskq26az4ajg73ufx33cf4gf2a"
},
"mimeType": "image/png",
"size": 32236
},
"path": "/packages/kreuzberg",
"publishedAt": "2026-05-10T19:31:55.922Z",
"site": "https://pub.dev",
"textContent": "High-performance document intelligence library — extract text, metadata, tables from 97+ formats including PDF, DOCX, images, and email. Changelog excerpt: - Initial release candidate - Document extraction (text, metadata, tables) from 97+ formats - OCR via Tesseract, PaddleOCR, VLM backends - HTML-to-Markdown conversion - PDF rendering - Code intelligence via tree-sitter (248 languages) - MIME type detection (118+ extensions) - LLM-powered structured extraction - Batch document processing - Embeddings generation via ONNX Runtime",
"title": "v1.0.0 of kreuzberg",
"updatedAt": "2026-05-10T18:51:58.098Z"
}