# Sentence Transformers v5.4 — multimodal embeddings and rerankers

> The most-used Python library for sentence embeddings adds native multimodal encoding and reranking across text, images, audio and video.

- Org: Hugging Face
- Date: 2026-04-09
- Category: tool, repo
- Source: https://huggingface.co/blog/multimodal-sentence-transformers
- Canonical page: https://ai-tldr.dev/releases/sentence-transformers-5-4/

## In short

The de-facto embedding library ships v5.4 with first-class multimodal support — encode and rerank text, images, audio and video through the same API, with Qwen3-VL, Llama Nemotron, BGE-VL and Jina rerankers working out of the box.

## What it is

Sentence Transformers is the standard Python library for loading, running, and training embedding and reranker models. Version 5.4.0, released April 9 2026, adds native support for vision-language and other multimodal models so the same SentenceTransformer and CrossEncoder classes can encode text, images, audio and video, and score relevance between mixed-modality pairs. The Apache-2.0 repo is maintained by Hugging Face and hosts more than 15,000 pretrained models on the Hub.

## How it works

The SentenceTransformer class was restructured to auto-detect input modality and route each item through the right encoder; a new Router module can compose separate encoders per modality in one pipeline. The CrossEncoder class was rewritten to inherit from a shared BaseModel with inspectable module chains and a new LogitScore module that unlocks generative rerankers. Text-only paths gained Flash Attention 2 input flattening, which concatenates variable-length sequences into flat tensors to cut padding waste when batch sequence lengths vary.

## Why it matters

Multimodal RAG has been a DIY mess: every model shipped with its own loader, and mixing text and image embeddings meant stitching scripts together. With v5.4 you can drop Qwen3-VL-Embedding, NVIDIA Llama Nemotron, BGE-VL or Jina Reranker into an existing Sentence Transformers pipeline without changing calling code. In practice that means visual document retrieval and cross-modal search work the same way people already wrote their text-only retrieval code.

## Who it's for

Anyone building retrieval, RAG or search pipelines who wants images, audio, or video on equal footing with text.

## Try it

pip install -U sentence-transformers

## Links

- [Announcement](https://huggingface.co/blog/multimodal-sentence-transformers)
- [Repo](https://github.com/huggingface/sentence-transformers)
- [Release notes](https://github.com/huggingface/sentence-transformers/releases/tag/v5.4.0)
- [Docs](https://sbert.net/)