🐦 Twitter Post Details

Viewing enriched Twitter post

@llama_index

EmbeddingGemma, a compact 308M parameter multilingual embedding model, perfect for on-device RAG applications - and we've made it super easy to integrate with LlamaIndex! 🛠️ Ready-to-use integration with LlamaIndex's @huggingface Embedding class - just specify the query and document prompts The model achieves top rankings on the Massive Text Embedding Benchmark while being small enough for mobile devices. Plus, it's easily fine-tunable - the blog shows how fine-tuning on medical data created a model that outperforms much larger alternatives. We love seeing efficient models like this that make powerful embeddings accessible everywhere, especially for edge deployments where every MB counts. See the full technical deep-dive and integration examples: https://t.co/AmMtCEkgKD

Media 1
Media 2

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1976346965379260916/media_0.jpg?",
      "filename": "media_0.jpg"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1976346965379260916/media_1.png?",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2025-10-12T13:39:42.649726",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1976346965379260916",
  "url": "https://x.com/llama_index/status/1976346965379260916",
  "twitterUrl": "https://twitter.com/llama_index/status/1976346965379260916",
  "text": "EmbeddingGemma, a compact 308M parameter multilingual embedding model, perfect for on-device RAG applications - and we've made it super easy to integrate with LlamaIndex!\n\n🛠️ Ready-to-use integration with LlamaIndex's @huggingface Embedding class - just specify the query and document prompts\n\nThe model achieves top rankings on the Massive Text Embedding Benchmark while being small enough for mobile devices. Plus, it's easily fine-tunable - the blog shows how fine-tuning on medical data created a model that outperforms much larger alternatives.\n\nWe love seeing efficient models like this that make powerful embeddings accessible everywhere, especially for edge deployments where every MB counts.\n\nSee the full technical deep-dive and integration examples: https://t.co/AmMtCEkgKD",
  "source": "Twitter for iPhone",
  "retweetCount": 24,
  "replyCount": 4,
  "likeCount": 156,
  "quoteCount": 1,
  "viewCount": 13147,
  "createdAt": "Thu Oct 09 18:00:09 +0000 2025",
  "lang": "en",
  "bookmarkCount": 112,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1976346965379260916",
  "displayTextRange": [
    0,
    276
  ],
  "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": 102542,
    "following": 28,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1434,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1739,
    "statusesCount": 3582,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "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/o817W5qBpx",
        "expanded_url": "https://twitter.com/llama_index/status/1976346965379260916/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1976346961906380800",
        "indices": [
          277,
          300
        ],
        "media_key": "3_1976346961906380800",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARttZRc5WjAACgACG21lGAhaIfQAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG21lFzlaMAAKAAIbbWUYCFoh9AAA",
            "media_key": "3_1976346961906380800"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G21lFzlaMAA6KXN.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 581,
              "w": 1038,
              "x": 81,
              "y": 0
            },
            {
              "h": 581,
              "w": 581,
              "x": 310,
              "y": 0
            },
            {
              "h": 581,
              "w": 510,
              "x": 345,
              "y": 0
            },
            {
              "h": 581,
              "w": 291,
              "x": 455,
              "y": 0
            },
            {
              "h": 581,
              "w": 1200,
              "x": 0,
              "y": 0
            }
          ],
          "height": 581,
          "width": 1200
        },
        "sizes": {
          "large": {
            "h": 581,
            "w": 1200
          }
        },
        "type": "photo",
        "url": "https://t.co/o817W5qBpx"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "urls": [
      {
        "display_url": "huggingface.co/blog/embedding…",
        "expanded_url": "https://huggingface.co/blog/embeddinggemma#llamaindex",
        "indices": [
          761,
          784
        ],
        "url": "https://t.co/AmMtCEkgKD"
      }
    ],
    "user_mentions": [
      {
        "id_str": "778764142412984320",
        "indices": [
          218,
          230
        ],
        "name": "Hugging Face",
        "screen_name": "huggingface"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}