🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

This is a fantastic tutorial showing you how to build a real-time, production-grade document processing pipeline over massive volumes of data for AI agents. The key insights here are to use streaming infrastructure to combine document processing, embedding, and indexing into a downstream system. ✅ LlamaParse for document parsing ✅ Apache Kafka for message broker, Flink for stream processing on Kafka ✅ MongoDB for storage Check it out: https://t.co/22iDxHHYC9 LlamaCloud: https://t.co/XYZmx5T7JA

Media 1
Media 2
Media 3
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_1.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_1.jpg?",
      "type": "photo",
      "filename": "media_1.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_2.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968477920189415747/media_2.jpg?",
      "type": "photo",
      "filename": "media_2.jpg"
    }
  ],
  "processed_at": "2025-09-18T13:48:04.242615",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1968477920189415747",
  "url": "https://x.com/jerryjliu0/status/1968477920189415747",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/1968477920189415747",
  "text": "This is a fantastic tutorial showing you how to build a real-time, production-grade document processing pipeline over massive volumes of data for AI agents.\n\nThe key insights here are to use streaming infrastructure to combine document processing, embedding, and indexing into a downstream system.\n\n✅ LlamaParse for document parsing\n✅ Apache Kafka for message broker, Flink for stream processing on Kafka\n✅ MongoDB for storage\n\nCheck it out: https://t.co/22iDxHHYC9\nLlamaCloud: https://t.co/XYZmx5T7JA",
  "source": "Twitter for iPhone",
  "retweetCount": 17,
  "replyCount": 3,
  "likeCount": 122,
  "quoteCount": 1,
  "viewCount": 14339,
  "createdAt": "Thu Sep 18 00:51:23 +0000 2025",
  "lang": "en",
  "bookmarkCount": 166,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1968477920189415747",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "jerryjliu0",
    "url": "https://x.com/jerryjliu0",
    "twitterUrl": "https://twitter.com/jerryjliu0",
    "id": "369777416",
    "name": "Jerry Liu",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "",
    "followers": 65236,
    "following": 1378,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 7849,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1282,
    "statusesCount": 6148,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "co-founder/CEO @llama_index\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "llamaindex.ai/careers",
              "expanded_url": "https://www.llamaindex.ai/careers",
              "indices": [
                38,
                61
              ],
              "url": "https://t.co/EUnMNmbCtx"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/Ht5jwxSrQB"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                15,
                27
              ],
              "name": "",
              "screen_name": "llama_index"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/YiIfjVlzb6"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/Odf5GPGpzF",
        "expanded_url": "https://twitter.com/jerryjliu0/status/1968477920189415747/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1968477912622886913",
        "indices": [
          280,
          303
        ],
        "media_key": "3_1968477912622886913",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARtRcDtqFvABCgACG1FwPS0XAUMAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG1FwO2oW8AEKAAIbUXA9LRcBQwAA",
            "media_key": "3_1968477912622886913"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G1FwO2oW8AEeIhr.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 446,
              "w": 796,
              "x": 0,
              "y": 0
            },
            {
              "h": 796,
              "w": 796,
              "x": 0,
              "y": 0
            },
            {
              "h": 900,
              "w": 789,
              "x": 0,
              "y": 0
            },
            {
              "h": 900,
              "w": 450,
              "x": 0,
              "y": 0
            },
            {
              "h": 900,
              "w": 796,
              "x": 0,
              "y": 0
            }
          ],
          "height": 900,
          "width": 796
        },
        "sizes": {
          "large": {
            "h": 900,
            "w": 796
          }
        },
        "type": "photo",
        "url": "https://t.co/Odf5GPGpzF"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "urls": [
      {
        "display_url": "mongodb.com/company/blog/t…",
        "expanded_url": "https://www.mongodb.com/company/blog/technical/building-scalable-document-processing-pipeline-llamaparse-confluent-cloud",
        "indices": [
          442,
          465
        ],
        "url": "https://t.co/22iDxHHYC9"
      },
      {
        "display_url": "cloud.llamaindex.ai",
        "expanded_url": "https://cloud.llamaindex.ai/",
        "indices": [
          478,
          501
        ],
        "url": "https://t.co/XYZmx5T7JA"
      }
    ]
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "1968412250424885451",
    "url": "https://x.com/llama_index/status/1968412250424885451",
    "twitterUrl": "https://twitter.com/llama_index/status/1968412250424885451",
    "text": "Learn how to build production-ready document processing pipelines that scale with real-time streaming architectures.\n\nThis comprehensive guide shows you how to combine LlamaParse with @confluentinc and @mongodb to create intelligent document processing systems that handle everything from complex PDFs to real-time embeddings:\n\n📄 Extract structured data from complex PDFs using LlamaParse's intelligent parsing that preserves tables, images, headers, and formatting context - going beyond simple OCR to understand document layout and meaning\n\n🔄 Build streaming data pipelines with Confluent and Apache Flink that process documents in real-time, generate embeddings, and handle schema evolution gracefully\n\n💾 Store and query processed documents with MongoDB Atlas Vector Search, combining structured data and embeddings in a single platform for powerful semantic search capabilities\n\n⚡ Implement real-time materialized views using MongoDB Atlas Stream Processing to avoid expensive joins and create query-optimized collections that update continuously\n\n🤖 Accelerate AI development with the new MongoDB MCP Server integration for VS Code\n\nRead the full architecture guide with code examples: https://t.co/hBwJIDpcxw",
    "source": "Twitter for iPhone",
    "retweetCount": 14,
    "replyCount": 4,
    "likeCount": 84,
    "quoteCount": 2,
    "viewCount": 21516,
    "createdAt": "Wed Sep 17 20:30:26 +0000 2025",
    "lang": "en",
    "bookmarkCount": 73,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "1968412250424885451",
    "displayTextRange": [
      0,
      273
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "llama_index",
      "url": "https://x.com/llama_index",
      "twitterUrl": "https://twitter.com/llama_index",
      "id": "1604278358296055808",
      "name": "LlamaIndex 🦙",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1758023766",
      "description": "",
      "location": "",
      "followers": 101694,
      "following": 28,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 1435,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 1723,
      "statusesCount": 3558,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "1958564769188978822"
      ],
      "profile_bio": {
        "description": "Build AI agents over your documents\n\nGithub: https://t.co/HC19j7veGE\nDocs: https://t.co/QInqg2yMCJ\nLlamaCloud: https://t.co/yQGTiRSfFL",
        "entities": {
          "description": {
            "urls": [
              {
                "display_url": "github.com/run-llama/llam…",
                "expanded_url": "http://github.com/run-llama/llama_index",
                "indices": [
                  45,
                  68
                ],
                "url": "https://t.co/HC19j7veGE"
              },
              {
                "display_url": "docs.llamaindex.ai",
                "expanded_url": "http://docs.llamaindex.ai",
                "indices": [
                  75,
                  98
                ],
                "url": "https://t.co/QInqg2yMCJ"
              },
              {
                "display_url": "cloud.llamaindex.ai",
                "expanded_url": "https://cloud.llamaindex.ai/",
                "indices": [
                  111,
                  134
                ],
                "url": "https://t.co/yQGTiRSfFL"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "llamaindex.ai",
                "expanded_url": "https://www.llamaindex.ai/",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/epzefqPT9Z"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "display_url": "pic.twitter.com/gAUdEseCV5",
          "expanded_url": "https://twitter.com/llama_index/status/1968412250424885451/photo/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "features": {
            "large": {},
            "orig": {}
          },
          "id_str": "1968412246046031872",
          "indices": [
            274,
            297
          ],
          "media_key": "3_1968412246046031872",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARtRNII5GkAACgACG1E0gz4aQMsAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABG1E0gjkaQAAKAAIbUTSDPhpAywAA",
              "media_key": "3_1968412246046031872"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/G1E0gjkaQAA93qH.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 1096,
                "w": 1958,
                "x": 0,
                "y": 0
              },
              {
                "h": 1958,
                "w": 1958,
                "x": 0,
                "y": 0
              },
              {
                "h": 2214,
                "w": 1942,
                "x": 0,
                "y": 0
              },
              {
                "h": 2214,
                "w": 1107,
                "x": 0,
                "y": 0
              },
              {
                "h": 2214,
                "w": 1958,
                "x": 0,
                "y": 0
              }
            ],
            "height": 2214,
            "width": 1958
          },
          "sizes": {
            "large": {
              "h": 2048,
              "w": 1811
            }
          },
          "type": "photo",
          "url": "https://t.co/gAUdEseCV5"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "urls": [
        {
          "display_url": "mongodb.com/company/blog/t…",
          "expanded_url": "https://www.mongodb.com/company/blog/technical/building-scalable-document-processing-pipeline-llamaparse-confluent-cloud",
          "indices": [
            1190,
            1213
          ],
          "url": "https://t.co/hBwJIDpcxw"
        }
      ],
      "user_mentions": [
        {
          "id_str": "2827342884",
          "indices": [
            184,
            197
          ],
          "name": "Confluent",
          "screen_name": "confluentinc"
        },
        {
          "id_str": "18080585",
          "indices": [
            202,
            210
          ],
          "name": "MongoDB",
          "screen_name": "mongodb"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}