{
  "user": {
    "created_at": "2011-09-07T22:54:31.000Z",
    "default_profile_image": false,
    "description": "co-founder/CEO @llama_index\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
    "fast_followers_count": 0,
    "favourites_count": 7173,
    "followers_count": 54387,
    "friends_count": 1364,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 1136,
    "location": "",
    "media_count": 1063,
    "name": "Jerry Liu",
    "normal_followers_count": 54387,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "screen_name": "jerryjliu0",
    "statuses_count": 5321,
    "translator_type": "none",
    "url": "https://t.co/YiIfjVlzb6",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "369777416"
  },
  "id": "1849968244913996017",
  "conversation_id": "1849968244913996017",
  "full_text": "Excited to feature this @nvidia case study on a sales research copilot - not only is it an ROI-generating use case 📈, there's a lot of useful bits on how to properly architect your agent to optimize performance/speed/cost ⚙️⚡️\n\n1. Route a user query to a top-performing model (llama3.1-405b) to directly answer the question, or to a cheaper model (llama3.1-70b) that knows less but can do RAG synthesis over documents\n\n2. parallel retrieval to combine information from data sources, like internal documents, NVIDIA's own website, and the open internet through perplexity\n\n3. Model each query prompt with the relevant acronyms. By decomposing your workflow into steps, you can also have more modular prompts that contain acronym subsets\n\nBlog: https://t.co/yoPuoS5F6x\n\nBuilt on top of @llama_index workflows. If you're new to workflows, come check it out! https://t.co/YnZYWKgdQj",
  "reply_count": 3,
  "retweet_count": 42,
  "favorite_count": 169,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [
    {
      "id_str": "61559439",
      "name": "NVIDIA",
      "screen_name": "nvidia",
      "profile": "https://twitter.com/nvidia"
    }
  ],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GaxnVOiaAAA2M4Z.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/jerryjliu0/status/1849968244913996017",
  "created_at": "2024-10-26T00:16:14.000Z",
  "#sort_index": "1849968244913996017",
  "view_count": 21697,
  "quote_count": 2,
  "is_quote_tweet": true,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "quoted_tweet": {
    "user": {
      "created_at": "2022-12-18T00:52:44.000Z",
      "default_profile_image": false,
      "description": "Build LLM agents over your data\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nDiscord: https://t.co/3ktq3zzYII",
      "fast_followers_count": 0,
      "favourites_count": 1261,
      "followers_count": 82611,
      "friends_count": 26,
      "has_custom_timelines": false,
      "is_translator": false,
      "listed_count": 1366,
      "location": "",
      "media_count": 1375,
      "name": "LlamaIndex 🦙",
      "normal_followers_count": 82611,
      "possibly_sensitive": false,
      "profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1696908553",
      "profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
      "screen_name": "llama_index",
      "statuses_count": 2997,
      "translator_type": "none",
      "url": "https://t.co/epzefqQqZx",
      "verified": true,
      "withheld_in_countries": [],
      "id_str": "1604278358296055808"
    },
    "id": "1849847301680005583",
    "conversation_id": "1849847301680005583",
    "full_text": "We are thrilled to announce a case study of a successful internal deployment of LlamaIndex at @nvidia, an internal AI assistant for sales 🧑‍💼🤖\n\n* Uses Llama 3.1 405b for simple queries, 70b model for document searches\n* Retrieves from multiple sources: internal docs, NVIDIA site, and web\n* LlamaIndex Workflows handles routing and core functionality\n* @chainlit_io provides the chat interface for sales reps\n* Parallel retrieval system searches multiple sources simultaneously\n* Built-in context augmentation helps handle company acronyms/terms\n* Real-time inference achieved through NVIDIA NIM optimization\n\nSales automation is a top use case for agents. Check out our case study here: https://t.co/AApFNVjp0v",
    "reply_count": 5,
    "retweet_count": 74,
    "favorite_count": 275,
    "hashtags": [],
    "symbols": [],
    "user_mentions": [
      {
        "id_str": "61559439",
        "name": "NVIDIA",
        "screen_name": "nvidia",
        "profile": "https://twitter.com/nvidia"
      }
    ],
    "urls": [],
    "media": [
      {
        "media_url": "https://pbs.twimg.com/media/Gav6TKdaQAADt6P.jpg",
        "type": "photo"
      }
    ],
    "url": "https://twitter.com/llama_index/status/1849847301680005583",
    "created_at": "2024-10-25T16:15:39.000Z",
    "#sort_index": "1849968244913996000",
    "view_count": 51185,
    "quote_count": 4,
    "is_quote_tweet": false,
    "is_retweet": false,
    "is_pinned": false,
    "is_truncated": true
  },
  "startUrl": "https://x.com/jerryjliu0/status/1849968244913996017"
}