Jina AI(@JinaAI_)
jina-embeddings-v5-omni 来了！我们的首个通用嵌入模型，支持文本、图像、音频和视频。
7.5Score
TL;DR · AI 摘要
Jina AI 发布了首个通用嵌入模型 v5-omni，支持文本、图像、音频和视频，提供两种尺寸，支持 Matryoshka 截断。
核心要点
- v5-omni 支持文本、图像、音频和视频的多模态嵌入。
- 提供两种尺寸：small (1.57B, 1024-dim, 32K context) 和 nano (0.95B, 768-dim, 8K context)。
- 支持 Matryoshka 截断，最小可截断至 32 维。
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- v5-omni 嵌入模型
- 引言
- 模型规格
- small (1.57B, 1024-dim, 32K context)
- nano (0.95B, 768-dim, 8K context)
- 功能特点
- Matryoshka 截断至 32 维
- 兼容性
金句 / Highlights
值得收藏与分享的关键句。
v5-omni is our first universal embedding model for text, images, audio, and video.
Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context).
Both support Matryoshka truncation down to 32 dimensions.
#Jina AI#嵌入模型#多模态
打开原文v5-omni is https://t.co/P4e4bOlKd5" / X
Jina AI on X: "jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is https://t.co/P4e4bOlKd5" / X
Don’t miss what’s happening
jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.
1:00
·
6
30
229
176
Read 6 replies