{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreic3elnbksgcnpj4g7wbt4d4aczb3hbrf3ckxgsomobzhmimcyzvv4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3miqw6u6zoml2"
  },
  "path": "/t/docling-studio-open-source-visual-inspection-tool-for-docling-pipelines/174983#post_1",
  "publishedAt": "2026-04-05T08:46:37.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "github.com/scub-france/Docling-Studio",
    "Docling Studio on HF Spaces"
  ],
  "textContent": "Hey everyone\n\nI built **Docling Studio** , an open-source visual inspection layer for Docling.\n\n**The problem:** if you’ve used Docling, you know the extraction engine is powerful — but validating outputs means digging through JSON and mentally mapping bounding box coordinates back to the original pages. No visual feedback loop.\n\n**What Docling Studio does:**\n\n  * Upload a PDF, configure your pipeline (OCR engine, table extraction, enrichment)\n\n  * Run the conversion\n\n  * Visually inspect every detected element — bounding boxes overlaid on original pages, element types, content preview on click\n\n  * Two modes: local (embedded Docling) or remote (Docling Serve)\n\n\n\n\nStack: Vue 3 / TypeScript + FastAPI / Python, fully Dockerized (multi-arch), 180+ tests.\n\n**Why it matters for RAG workflows:** without seeing what Docling extracts, it’s hard to evaluate chunk quality before feeding your pipeline. Docling Studio gives you that feedback loop.\n\n**Repo:** github.com/scub-france/Docling-Studio\n**Try it:** Docling Studio on HF Spaces\n\nThe project is part of the Docling ecosystem (Linux Foundation AI & Data). Feedback, issues, and contributions welcome — especially interested in hearing what features would help your document AI workflows.",
  "title": "Docling Studio — open-source visual inspection tool for Docling pipelines"
}