🐦 Twitter Post Details

Viewing enriched Twitter post

@_inesmontani

The first version of my spaCy + Docling integration is here: 📚 process PDFs, Word documents & more 📝 structured text-based output via @spacy_io's Doc 🏷 layout spans for sections, headings etc. 🔮 apply NLP pipelines to PDFs ✂️ chunk your data for RAG https://t.co/PNbGNNrom1

View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1858846762636571032/media_0.jpg",
      "type": "photo",
      "original_url": "https://pbs.twimg.com/media/GcvzQhrWEAAD2mE.jpg",
      "download_date": "2025-08-13T05:53:12.896872",
      "stored_in_supabase": true,
      "format_converted_from_list": true
    }
  ],
  "conversion_date": "2025-08-13T00:32:38.835349",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2008-05-02T02:18:57.000Z",
    "default_profile_image": false,
    "description": "💥 Founder & CEO @explosion_ai\n👩‍💻 Dev @spacy_io & https://t.co/LIBUg29Gm9\n\n🐘 https://t.co/pqYinNyTPm\n🟦 https://t.co/RjrWCh1I27…\n💼 https://t.co/gXMmVHWM1m",
    "fast_followers_count": 0,
    "favourites_count": 6041,
    "followers_count": 21553,
    "friends_count": 340,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 518,
    "location": "Berlin, Germany",
    "media_count": 669,
    "name": "Ines Montani 〰️",
    "normal_followers_count": 21553,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/14622002/1562699707",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/762577401574526976/hQjD1Z-F_normal.jpg",
    "screen_name": "_inesmontani",
    "statuses_count": 3684,
    "translator_type": "none",
    "url": "https://t.co/zeTfk0AMPK",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "14622002"
  },
  "id": "1858846762636571032",
  "conversation_id": "1858846762636571032",
  "full_text": "The first version of my spaCy + Docling integration is here:\n\n📚 process PDFs, Word documents &amp; more\n📝 structured text-based output via @spacy_io's Doc\n🏷 layout spans for sections, headings etc.\n🔮 apply NLP pipelines to PDFs\n✂️ chunk your data for RAG https://t.co/PNbGNNrom1",
  "reply_count": 3,
  "retweet_count": 13,
  "favorite_count": 68,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [
    {
      "id_str": "3422200198",
      "name": "spaCy",
      "screen_name": "spacy_io",
      "profile": "https://twitter.com/spacy_io"
    }
  ],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GcvzQhrWEAAD2mE.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/_inesmontani/status/1858846762636571032",
  "created_at": "2024-11-19T12:16:18.000Z",
  "#sort_index": "1858846762636571032",
  "view_count": 3949,
  "quote_count": 0,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "startUrl": "https://x.com/_inesmontani/status/1858846762636571032"
}