Sentence Transformers
Embeddings, rerankers, and sparse encoders for sentence, text and image.
Open-source Python framework for creating, training, and using embedding, reranker, and sparse-encoder models for semantic search and related text retrieval tasks.
Recent stories
2 linked stories
releasePRIMARY2026-08-18
Sentence Transformers 6.0 adds MultiVectorEncoder for late-interaction retrieval
Sentence Transformers 6.0 adds MultiVectorEncoder for ColBERT-style training, inference, and interpretation, including visual-document retrieval. Index size can increase substantially: 4,874 passages expanded to 608,414 token vectors in one example.
releasePRIMARY2026-05-12
Sentence Transformers 5.5.0 adds train-sentence-transformers skill with one-shot 0.8856 NDCG@10
Sentence Transformers 5.5.0 adds an agent skill for fine-tuning embeddings, rerankers, and sparse encoders from Claude Code, Codex, Cursor, and Gemini CLI. The author reports a one-shot German embedding run rising from 0.6720 to 0.8856 NDCG@10 on a local PC.