Sentence Transformers 推出多模態嵌入與重排（Reranker）模型支援
Original: Multimodal Embedding & Reranker Models with Sentence Transformers
The popular open-source library `sentence-transformers` from Hugging Face has received a major update, officially introducing native…
Hugging Face 宣布其熱門開源庫 Sentence Transformers 正式支援多模態（Multimodal）嵌入與重排（Reranker）模型。開發者現在可以使用統一的 API 同時處理文本與影像，將它們映射到相同的向量空間中。這項更新大幅降低了建構多模態 RAG、圖文搜尋與跨模態推薦系統的門檻。
The popular open-source library `sentence-transformers` from Hugging Face has received a major update, officially introducing native support for Multimodal Embeddings and Multimodal Reranker models. This means developers no longer need to manually integrate multiple separate vision and text model libraries — they can achieve efficient cross-modal retrieval within a single unified framework.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Related
Summaries are AI-generated; the original article is authoritative.