{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidapwjq6r4x2vqrolnibc66627og4s3yej7567krvqkfjuwjhcini",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mouohmh7wyw2"
  },
  "path": "/t/seeking-indic-document-dataset-india-invoices-receipts-utility-bills-payment-advices-packing-lists-commercial-invoices-credit-notes/177055#post_2",
  "publishedAt": "2026-06-22T09:25:19.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "You may want to explore Hugging Face, AI4Bharat, and Bhashini resources, but high-quality, commercially licensable Indic business-document datasets with JSON annotations are still quite rare. For the scale and accuracy you need, a custom annotation vendor or synthetic data generation pipeline may be the most practical option.",
  "title": "[SEEKING] Indic Document Dataset (India) — Invoices, Receipts, Utility Bills, Payment Advices, Packing Lists, Commercial Invoices, Credit Notes"
}