{
  "user": {
    "created_at": "2007-05-29T00:21:54.000Z",
    "default_profile_image": false,
    "description": "CEO of @abacusai, the AI-assisted data-science & LLMOps platform to build applied AI systems at scale, ex-AWS / Google, passionate about human behavior",
    "fast_followers_count": 0,
    "favourites_count": 6006,
    "followers_count": 89089,
    "friends_count": 400,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 1159,
    "location": "San Francisco, CA",
    "media_count": 485,
    "name": "Bindu Reddy",
    "normal_followers_count": 89089,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/6398252/1689653510",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1443737943684763651/32WHA-kg_normal.jpg",
    "screen_name": "bindureddy",
    "statuses_count": 10611,
    "translator_type": "none",
    "url": "https://t.co/QA1YZ10l2F",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "6398252"
  },
  "id": "1694807254527320171",
  "conversation_id": "1694807254527320171",
  "full_text": "Data LLM - An AI Brain That Extracts Insights From Your Data\n\nYour data always has a story to tell, but most organizations don't know what it is. Data LLMs can understand the patterns in your data and extract hidden insights from it.  \n\nMuch like a custom ChatGPT on all your data, you can simply chat with it to understand the key equations that drive your business.\n\nHowever, there are a number of steps involved in setting up your DataLLM. The good news is you can leverage GPT-4 or any other LLM of your choice\n\nHow it works -  Fundamentally, we will have to orchestrate between LLMs and your data sources to extract the right response to a query.  For example: your query could be - how many users churned in Q1.  We will have to look this up in the source database by executing the right SQL query,  retrieving the results, and then summarizing them.  \n\nYou might then have an ongoing conversation with the DataLLM and ask a follow-up question. The system has to keep state, execute appropriate queries, understand the results, and generate responses.\n\nA considerable amount of set-up is involved before this can work smoothly\n\nConnector set-up:  Your data probably resides in multiple databases or data warehouses like Snowflake or BigQuery. You will have to set up connectors to all your data sources. Ideally, you want to run your queries on the source database. Moving data is costly and is not recommended\n\nDoc retrievers: This is a component that has all the metadata about your data. Typically you can use a vector store for this component. This module knows about your database structure and has details about the table names and columns. We have to use information from the doc retriever to feed to the LLM to construct the SQL queries\n\nOrchestration layer: This is a hard one and is the layer that talks to the LLM, doc retriever, and your database. When the query comes in the orchestrator will ask the doc retriever for the relevant tables and meta-data that map to the query. It will then send the query along with the meta-data to the LLM will will generate the SQL query. \n\nThe orchestrator then routes the SQL query to the data source where it gets executed. Once the results are returned, you will have to make one more call to the LLM to summarize these results. Sometimes, multiple SQL queries are required for harder more nuanced questions\n\nLLMs: You can use closed-source (e.g. GPT-4) or your own custom LLM (Abacus-Giraffe or Llama2).  You can compare and contrast whichever LLM works for you and pick the best one\n\nUX Interface: Last but not least, you will ideally want a ChatGPT-like interface with the ability to track history, have threaded conversations, and display tables and charts.\n\nDataLLMs can dramatically increase the efficacy of your organization. By making it easy to extract insights from your data, your employees will more often than not, make data-driven decisions. They are much more effective than having to go through a mountain of reports that no one looks at.\n\nAbacus can set up a DataLLM for you in a couple of days. We will even do it for free, to showcase how useful it can be. \n\nBlog link: https://t.co/0SfXmJgoRr",
  "reply_count": 26,
  "retweet_count": 185,
  "favorite_count": 868,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/F4UpcL2bIAIlGV_.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/bindureddy/status/1694807254527320171",
  "created_at": "2023-08-24T20:21:52.000Z",
  "#sort_index": "1694807254527320171",
  "view_count": 182537,
  "quote_count": 9,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://twitter.com/bindureddy/status/1694807254527320171"
}