{
  "type": "tweet",
  "id": "2041638826091946450",
  "url": "https://x.com/itsclelia/status/2041638826091946450",
  "twitterUrl": "https://twitter.com/itsclelia/status/2041638826091946450",
  "text": "How can you improve your agentic search pipeline?\nI just wrote a blog post with @tech_optimist from @lancedb to answer exactly that.\nTLDR:\n- Parse files and take page-level screenshots with LiteParse, the parser we just open sourced at @llama_index\n- Chunk and embed text, and store everything (text, image bytes, vector data) in a local LanceDB instance\n- Expose text and image retrieval tools to a Claude agent, and let it reason on both data types\n\nWith our eval dataset, the agent got near-perfect scores on most complex QA tasks, showing how a strong parsing foundation and multimodal retrieval can really improve your search🚀\nRead the full breakdown here: https://t.co/5GRRy065TI",
  "source": "Twitter for iPhone",
  "retweetCount": 2,
  "replyCount": 0,
  "likeCount": 6,
  "quoteCount": 0,
  "viewCount": 636,
  "createdAt": "Tue Apr 07 22:06:42 +0000 2026",
  "lang": "en",
  "bookmarkCount": 3,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2041638826091946450",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "itsclelia",
    "url": "https://x.com/itsclelia",
    "twitterUrl": "https://twitter.com/itsclelia",
    "id": "1925178481534509056",
    "name": "Clelia Bertelli (🦙/acc)",
    "isVerified": false,
    "isBlueVerified": false,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/2010129136501555200/gaI8nXYh_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1925178481534509056/1773305599",
    "description": "she/her |\nOpen Sourceress at @llama_index 🦙 | \nGirly dev building AI things in python💅 | Cheating on python with Go and Rust🦫🦀",
    "location": "",
    "followers": 779,
    "following": 382,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Wed May 21 13:15:29 +0000 2025",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {
        "urls": [
          {
            "display_url": "clelia.dev",
            "expanded_url": "https://clelia.dev",
            "indices": [
              0,
              23
            ],
            "url": "https://t.co/zhCyKugORT"
          }
        ]
      }
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1387,
    "hasCustomTimelines": false,
    "isTranslator": false,
    "mediaCount": 145,
    "statusesCount": 795,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2040111180203892928"
    ],
    "profile_bio": {},
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/Sq88vO7H4i",
        "expanded_url": "https://x.com/itsclelia/status/2041638826091946450/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 69,
                "w": 69,
                "x": 1238,
                "y": 610
              }
            ]
          },
          "medium": {
            "faces": [
              {
                "h": 60,
                "w": 60,
                "x": 1079,
                "y": 531
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 69,
                "w": 69,
                "x": 1238,
                "y": 610
              }
            ]
          },
          "small": {
            "faces": [
              {
                "h": 34,
                "w": 34,
                "x": 611,
                "y": 301
              }
            ]
          }
        },
        "id_str": "2041638822937817088",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2041638822937817088",
        "media_results": {
          "result": {
            "media_key": "3_2041638822937817088"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HFVbsUDa8AAubT1.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 768,
              "w": 1371,
              "x": 0,
              "y": 0
            },
            {
              "h": 768,
              "w": 768,
              "x": 0,
              "y": 0
            },
            {
              "h": 768,
              "w": 674,
              "x": 0,
              "y": 0
            },
            {
              "h": 768,
              "w": 384,
              "x": 116,
              "y": 0
            },
            {
              "h": 768,
              "w": 1376,
              "x": 0,
              "y": 0
            }
          ],
          "height": 768,
          "width": 1376
        },
        "sizes": {
          "large": {
            "h": 768,
            "resize": "fit",
            "w": 1376
          },
          "medium": {
            "h": 670,
            "resize": "fit",
            "w": 1200
          },
          "small": {
            "h": 380,
            "resize": "fit",
            "w": 680
          },
          "thumb": {
            "h": 150,
            "resize": "crop",
            "w": 150
          }
        },
        "type": "photo",
        "url": "https://t.co/Sq88vO7H4i"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "lancedb.com/blog/smart-par…",
        "expanded_url": "https://www.lancedb.com/blog/smart-parsing-meets-sharp-retrieval-combining-liteparse-and-lancedb",
        "indices": [
          662,
          685
        ],
        "url": "https://t.co/5GRRy065TI"
      }
    ],
    "user_mentions": [
      {
        "id_str": "1928993071",
        "indices": [
          80,
          94
        ],
        "name": "Prashanth Rao",
        "screen_name": "tech_optimist"
      },
      {
        "id_str": "1648910047270010880",
        "indices": [
          100,
          108
        ],
        "name": "LanceDB",
        "screen_name": "lancedb"
      },
      {
        "id_str": "1604278358296055808",
        "indices": [
          236,
          248
        ],
        "name": "LlamaIndex 🦙",
        "screen_name": "llama_index"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "article": null
}