🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

Existing "OCR" technology for digitalizing PDFs has been around for ~30 years. Reading printed characters on a page and converting them into meaningful representations is a hard problem! Existing approaches were either dependent on pattern matching to specific document templates, or on specialized ML models for specific data distributions. They constantly needed template/model refitting and broke on the long-tail of varied docs. Today, vision models are capable of much higher general accuracy without constant retraining, but they still need careful orchestration to make sure that they're able to attend to specific elements (tables, charts), and output semantically correct outputs. Our OCR platform LlamaParse is built on this "agentic OCR" foundation. A network of specialized agents will parse apart even the most complicated documents and reconstruct the outputs in a semantically meaningful way. We're excited to reach a world where raw parsing accuracy is not just 80% over "easy" docs, but 100% accurate over literally any document that exists. Check it out: https://t.co/FeOoTjeKjf LlamaParse: https://t.co/TqP6OT5U5O

Media 1
Media 2

šŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032249462601728335/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032249462601728335/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032249462601728335/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032249462601728335/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    }
  ],
  "processed_at": "2026-03-13T15:32:02.325394",
  "pipeline_version": "2.0"
}

šŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2032249462601728335",
  "url": "https://x.com/jerryjliu0/status/2032249462601728335",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2032249462601728335",
  "text": "Existing \"OCR\" technology for digitalizing PDFs has been around for ~30 years. Reading printed characters on a page and converting them into meaningful representations is a hard problem! \n\nExisting approaches were either dependent on pattern matching to specific document templates, or on specialized ML models for specific data distributions. They constantly needed template/model refitting and broke on the long-tail of varied docs.\n\nToday, vision models are capable of much higher general accuracy without constant retraining, but they still need careful orchestration to make sure that they're able to attend to specific elements (tables, charts), and output semantically correct outputs. \n\nOur OCR platform LlamaParse is built on this \"agentic OCR\" foundation. A network of specialized agents will parse apart even the most complicated documents and reconstruct the outputs in a semantically meaningful way. We're excited to reach a world where raw parsing accuracy is not just 80% over \"easy\" docs, but 100% accurate over literally any document that exists.\n\nCheck it out: https://t.co/FeOoTjeKjf\nLlamaParse: https://t.co/TqP6OT5U5O",
  "source": "Twitter for iPhone",
  "retweetCount": 13,
  "replyCount": 7,
  "likeCount": 121,
  "quoteCount": 0,
  "viewCount": 11625,
  "createdAt": "Fri Mar 13 00:16:43 +0000 2026",
  "lang": "en",
  "bookmarkCount": 108,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2032249462601728335",
  "displayTextRange": [
    0,
    271
  ],
  "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": 70896,
    "following": 1463,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8528,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1442,
    "statusesCount": 6708,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2031525259120378097"
    ],
    "profile_bio": {
      "description": "document OCR + workflows @llama_index. cofounder/CEO\n\nCareers: https://t.co/EUnMNmb4DZ\nEnterprise: https://t.co/Ht5jwxRU13",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "llamaindex.ai/careers",
              "expanded_url": "https://www.llamaindex.ai/careers",
              "indices": [
                63,
                86
              ],
              "url": "https://t.co/EUnMNmb4DZ"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                99,
                122
              ],
              "url": "https://t.co/Ht5jwxRU13"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                25,
                37
              ],
              "name": "",
              "screen_name": "llama_index"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/YiIfjVl1ly"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/HrqaDZ6FQi",
        "expanded_url": "https://twitter.com/jerryjliu0/status/2032249462601728335/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2032246929858707457",
        "indices": [
          272,
          295
        ],
        "media_key": "3_2032246929858707457",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwz/dC+G0ABCgACHDQAHnFawU8AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHDP90L4bQAEKAAIcNAAecVrBTwAA",
            "media_key": "3_2032246929858707457"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HDP90L4bQAEbPiz.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 441,
              "w": 788,
              "x": 0,
              "y": 48
            },
            {
              "h": 489,
              "w": 489,
              "x": 299,
              "y": 0
            },
            {
              "h": 489,
              "w": 429,
              "x": 359,
              "y": 0
            },
            {
              "h": 489,
              "w": 245,
              "x": 526,
              "y": 0
            },
            {
              "h": 489,
              "w": 788,
              "x": 0,
              "y": 0
            }
          ],
          "height": 489,
          "width": 788
        },
        "sizes": {
          "large": {
            "h": 489,
            "w": 788
          }
        },
        "type": "photo",
        "url": "https://t.co/HrqaDZ6FQi"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "llamaindex.ai/blog/agentic-o…",
        "expanded_url": "https://www.llamaindex.ai/blog/agentic-ocr?utm_source=xjl&utm_medium=social",
        "indices": [
          1079,
          1102
        ],
        "url": "https://t.co/FeOoTjeKjf"
      },
      {
        "display_url": "cloud.llamaindex.ai/?utm_source=xj…",
        "expanded_url": "https://cloud.llamaindex.ai/?utm_source=xjl&utm_medium=social",
        "indices": [
          1115,
          1138
        ],
        "url": "https://t.co/TqP6OT5U5O"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2032170523615248615",
    "url": "https://x.com/llama_index/status/2032170523615248615",
    "twitterUrl": "https://twitter.com/llama_index/status/2032170523615248615",
    "text": "Ever wondered what we mean by 'agentic' OCR? It's parsing that reasons about documents instead of just reading them.\n\nAgentic OCR adapts to layout changes by treating document processing as a goal-oriented task rather than simple text extraction.\n\n🧠 Uses multimodal language models to understand document structure and context, not just convert pixels to text\nšŸ“ Provides visual grounding with bounding boxes so every extracted field traces back to its source location\nšŸ”„ Runs self-correction loops to catch inconsistencies before they reach your downstream systems\n⚔ Achieves 90-95%+ straight-through processing rates on new document formats without template setup\n\nThis matters for legal teams processing M&A due diligence, healthcare admins handling medical forms, and finance teams reconciling reports across subsidiaries. The agent doesn't just extract data - it completes document workflows with built-in validation and business logic.\n\nLlamaParse is our implementation of agentic OCR. Get 10,000 free credits to test it against your actual documents:\n\nRead the full breakdown: https://t.co/FRoyXKGUia",
    "source": "Twitter for iPhone",
    "retweetCount": 11,
    "replyCount": 7,
    "likeCount": 58,
    "quoteCount": 3,
    "viewCount": 16085,
    "createdAt": "Thu Mar 12 19:03:03 +0000 2026",
    "lang": "en",
    "bookmarkCount": 59,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2032170523615248615",
    "displayTextRange": [
      0,
      274
    ],
    "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 šŸ¦™",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": "Business",
      "profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1770092126",
      "description": "",
      "location": "",
      "followers": 110059,
      "following": 29,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 1504,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 1836,
      "statusesCount": 3763,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2029767312195117278"
      ],
      "profile_bio": {
        "description": "AI Agents for document OCR + workflows\n\nLlamaParse: https://t.co/yQGTiRSfFL\nDocs: https://t.co/us6GCS14vD",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [
              {
                "display_url": "cloud.llamaindex.ai",
                "expanded_url": "https://cloud.llamaindex.ai/",
                "indices": [
                  52,
                  75
                ],
                "url": "https://t.co/yQGTiRSfFL"
              },
              {
                "display_url": "developers.llamaindex.ai/python/cloud/",
                "expanded_url": "https://developers.llamaindex.ai/python/cloud/",
                "indices": [
                  82,
                  105
                ],
                "url": "https://t.co/us6GCS14vD"
              }
            ],
            "user_mentions": []
          },
          "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/2dJfA7WOpL",
          "expanded_url": "https://twitter.com/llama_index/status/2032170523615248615/photo/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "features": {
            "large": {
              "faces": []
            },
            "orig": {
              "faces": []
            }
          },
          "id_str": "2032170520842813440",
          "indices": [
            275,
            298
          ],
          "media_key": "3_2032170520842813440",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwzuFJh20AACgACHDO4UwcbQOcAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHDO4UmHbQAAKAAIcM7hTBxtA5wAA",
              "media_key": "3_2032170520842813440"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HDO4UmHbQAAVnX5.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 672,
                "w": 1200,
                "x": 0,
                "y": 0
              },
              {
                "h": 676,
                "w": 676,
                "x": 0,
                "y": 0
              },
              {
                "h": 676,
                "w": 593,
                "x": 0,
                "y": 0
              },
              {
                "h": 676,
                "w": 338,
                "x": 41,
                "y": 0
              },
              {
                "h": 676,
                "w": 1200,
                "x": 0,
                "y": 0
              }
            ],
            "height": 676,
            "width": 1200
          },
          "sizes": {
            "large": {
              "h": 676,
              "w": 1200
            }
          },
          "type": "photo",
          "url": "https://t.co/2dJfA7WOpL"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [
        {
          "display_url": "llamaindex.ai/blog/agentic-o…",
          "expanded_url": "https://www.llamaindex.ai/blog/agentic-ocr?utm_source=socials&utm_medium=li_social",
          "indices": [
            1082,
            1105
          ],
          "url": "https://t.co/FRoyXKGUia"
        }
      ],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}