{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib6ebmrac7zeyrkaitz2lxriqk4s2pizhvm7vjtnnt55hq65pa77i",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mit7zdux6r32"
  },
  "path": "/t/how-to-build-custom-key-value-extraction-similar-to-azure-document-intelligence/175015#post_1",
  "publishedAt": "2026-04-06T11:39:38.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Hi everyone,\n\nI’m trying to build a custom document understanding system and could use some guidance.\n\nCurrently, I’m using Azure Document Intelligence, where we can define specific fields and train a model by annotating documents. The trained model then extracts only the required key-value pairs from new documents.\n\nI’m interested in building a similar solution using open-source models available on Hugging Face, but I’m not sure where to begin.\n\nCould anyone suggest:\n\nSuitable models or approaches for extracting specific fields from documents\n\nRecommended workflows for training such a system\n\nThanks in advance for your help!",
  "title": "How to build custom key-value extraction (similar to Azure Document Intelligence)?"
}