Sentence Transformers Adds Multimodal Embedding and Reranker Model Support

Summary

Hugging Face has published a blog post by Tom Aarsen detailing new multimodal embedding and reranker capabilities in the Sentence Transformers library. The update extends the widely-used open-source library beyond text-only embeddings to support multimodal inputs — likely including images and text — for both embedding generation and reranking tasks. This is significant for retrieval-augmented generation (RAG) pipelines and search systems that need to handle diverse content types. The addition o