{
  "user": {
    "created_at": "2015-07-15T21:49:02.000Z",
    "default_profile_image": false,
    "description": "The modern cloud platform built on PostgreSQL for time series, events, and analytics (and vectors too!). GitHub ⭐ appreciated! https://t.co/9HK3eQHggD.",
    "fast_followers_count": 0,
    "favourites_count": 2835,
    "followers_count": 8330,
    "friends_count": 468,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 199,
    "location": "🌎 Employees Worldwide",
    "media_count": 1479,
    "name": "Timescale",
    "normal_followers_count": 8330,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/3377917289/1696461015",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1658849767865167876/hA5OXD9m_normal.jpg",
    "screen_name": "TimescaleDB",
    "statuses_count": 5199,
    "translator_type": "none",
    "url": "https://t.co/BT63UNEwTb",
    "verified": true,
    "verified_type": "Business",
    "withheld_in_countries": [],
    "id_str": "3377917289"
  },
  "id": "1853089038288527824",
  "conversation_id": "1853089038288527824",
  "full_text": "Optimizing RAG Chunking and Formatting Directly in Postgres with pgai Vectorizer 🚀\n\nIf you’ve built AI search engines, chatbots, or RAG systems, you know that good chunking and formatting can make or break the quality of your AI. But testing these strategies is tedious and complex.\n\nWith pgai Vectorizer, you can now experiment with RAG chunking and formatting directly in Postgres - users can easily test chunking strategies (like recursive character text splitting) and customize formatting to include metadata. It handles embeddings as a declarative feature, updating automatically when source data changes, allowing users to maintain and compare multiple configurations. This simplifies A/B testing, ensuring stability as new strategies roll out, with backward compatibility and zero downtime.\n\nPgai Vectorizer supports OpenAI embedding models and offers options for custom chunking in various formats (e.g., HTML), making it versatile across data types. Available on Timescale Cloud or self-hosted. Check out how pgai Vectorizer brings automated embedding management into Postgres for powerful, hassle-free testing. 🔗👇\n\n#Postgres #pgaiVectorizer #Data #AI #SQL #DevTools #AIDevelopment #PostgresExtensions #AIinSQL",
  "reply_count": 2,
  "retweet_count": 4,
  "favorite_count": 20,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/Gbd-qAGaMAAi-Qt.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/TimescaleDB/status/1853089038288527824",
  "created_at": "2024-11-03T14:57:10.000Z",
  "#sort_index": "1853089038288527824",
  "view_count": 2190,
  "quote_count": 0,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/timescaledb/status/1853089038288527824"
}