{
  "user": {
    "created_at": "2015-12-21T20:07:35.000Z",
    "default_profile_image": false,
    "description": "Bringing the power of machine learning to the web. Currently working on Transformers.js (@huggingface 🤗)",
    "fast_followers_count": 0,
    "favourites_count": 2641,
    "followers_count": 2588,
    "friends_count": 217,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 81,
    "location": "",
    "media_count": 104,
    "name": "Xenova",
    "normal_followers_count": 2588,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1628854727218798593/sWLzdtJ1_normal.jpg",
    "screen_name": "xenovacom",
    "statuses_count": 535,
    "translator_type": "none",
    "url": "https://t.co/n0HmaM7Wsb",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "4560264219"
  },
  "id": "1705385934072742015",
  "conversation_id": "1705385934072742015",
  "full_text": "When do you *really* need to use a vector database? 🤔 To try answer that question, I recreated my semantic image search application to run 100% in-browser with Transformers.js (no server).\n\nAfter loading the model and database, it only takes ~50ms to compute text embeddings and perform similarity search across 25k images.\n\nNo vector DB, just plain old JavaScript. I think @karpathy was onto something... 👀 What do you think?\n\n🔗 Demo site: https://t.co/CQSmghjdqd\n⌨️ Source code: https://t.co/cOBDFni0k7",
  "reply_count": 36,
  "retweet_count": 61,
  "favorite_count": 431,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1705373256755331072/pu/img/SFZShPGkxPMcEpDR.jpg",
      "type": "video",
      "video_url": "https://video.twimg.com/ext_tw_video/1705373256755331072/pu/vid/avc1/976x720/yjDlWYpCjd6j3eXP.mp4?tag=12"
    }
  ],
  "url": "https://twitter.com/xenovacom/status/1705385934072742015",
  "created_at": "2023-09-23T00:57:45.000Z",
  "#sort_index": "1705385934072742015",
  "view_count": 182712,
  "quote_count": 7,
  "is_quote_tweet": true,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "quoted_tweet": {
    "user": {
      "created_at": "2009-04-21T06:49:15.000Z",
      "default_profile_image": false,
      "description": "Building a kind of JARVIS @ OреոΑӏ. Previously Director of AI @ Tesla, CS231n, PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥",
      "fast_followers_count": 0,
      "favourites_count": 8919,
      "followers_count": 794217,
      "friends_count": 877,
      "has_custom_timelines": true,
      "is_translator": false,
      "listed_count": 10728,
      "location": "Stanford",
      "media_count": 636,
      "name": "Andrej Karpathy",
      "normal_followers_count": 794217,
      "possibly_sensitive": false,
      "profile_banner_url": "https://pbs.twimg.com/profile_banners/33836629/1407117611",
      "profile_image_url_https": "https://pbs.twimg.com/profile_images/1296667294148382721/9Pr6XrPB_normal.jpg",
      "screen_name": "karpathy",
      "statuses_count": 8356,
      "translator_type": "none",
      "url": "https://t.co/0EcFthjJXM",
      "verified": false,
      "withheld_in_countries": [],
      "id_str": "33836629"
    },
    "id": "1647374645316968449",
    "conversation_id": "1647372603907280896",
    "full_text": "@sinclanich np.array\npeople keep reaching for much fancier things way too fast these days",
    "reply_count": 20,
    "retweet_count": 96,
    "favorite_count": 1304,
    "hashtags": [],
    "symbols": [],
    "user_mentions": [
      {
        "id_str": "4117820354",
        "name": "Hugh Anon",
        "screen_name": "sinclanich",
        "profile": "https://twitter.com/sinclanich"
      }
    ],
    "urls": [],
    "media": [],
    "url": "https://twitter.com/karpathy/status/1647374645316968449",
    "created_at": "2023-04-15T23:01:36.000Z",
    "#sort_index": "1705385934072742000",
    "view_count": 639893,
    "quote_count": 61,
    "is_quote_tweet": false,
    "replying_to_tweet": "https://twitter.com/sinclanich/status/1647374385827958785",
    "is_retweet": false,
    "is_pinned": false,
    "is_truncated": false
  },
  "startUrl": "https://twitter.com/xenovacom/status/1705385934072742015"
}