sentence-transformers

Embeddings, Retrieval, and Reranking

sentence-transformers Permissive license Apache-2.0 Active ★ 18,999 v5.7.0 released 2026-08-06

Install

sentence-transformers on PyPI

pip

pip install sentence-transformers

uv

uv add sentence-transformers

poetry

poetry add sentence-transformers

Package facts

License	Apache-2.0 (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	9 — transformers, tokenizers, huggingface-hub, torch, numpy, scikit-learn, scipy, typing_extensions, tqdm
Maintenance	actively maintained — 7 days since the last release
Last repo commit	2026-08-13
First released	2019-07-25
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: sentence_transformers-5.7.0-py3-none-any.whl

Keywords: Transformer Networks, BERT, XLNet, sentence embedding, PyTorch, NLP, deep learning

Development Status :: 5 - Production/StableIntended Audience :: Science/ResearchProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Scientific/Engineering :: Artificial Intelligence

About sentence-transformers

from the package's own PyPI description — quoted content, verbatim

HF Models (image) [GitHub - License (image)][#github-license] [PyPI - Python Version (image)][#pypi-package] [PyPI - Package Version (image)][#pypi-package] [Docs - GitHub.io (image)][#docs-package]

Sentence Transformers: Embeddings, Retrieval, and Reranking

This framework provides an easy method to compute embeddings for accessing, using, and training state-of-the-art embedding and reranker models. It can be used to compute embeddings using Sentence Transformer models...

Read as markdown · JSON record · Source repository · Homepage

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Computes dense and sparse text embeddings, and reranking scores using pre-trained transformer models for semantic search, similarity, and information retrieval tasks.

Low friction: pure Python wheel with well-maintained dependencies including transformers, torch, and huggingface-hub. Active development—last commit 2026-08-13—signals strong community support.

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; derivative works and modifications are permitted provided the license and copyright notice are retained.

Usage

pip install sentence-transformers

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
embeddings = model.encode(["Hello world", "Hi there"])
print(embeddings.shape)

Requires Python 3.10+; PyTorch 1.11.0+ and transformers v4.41.0+ recommended per documentation.

Verdict: Production-ready embedding framework with no known vulnerabilities, active maintenance, and permissive Apache-2.0 licensing. Broad runtime dependency footprint (transformers, torch, numpy, scikit-learn, scipy, tokenizers, huggingface-hub, typing_extensions, tqdm) is standard for ML workloads; suitable for semantic search, retrieval, and reranking in research and production systems.

Needs verification

Whether pre-trained model downloads are cached locally or require network access on each instantiation
GPU memory requirements and inference speed benchmarks for typical embedding models
Compatibility with quantized or ONNX-format model variants beyond standard PyTorch models

text embeddings semantic searchsentence transformer modelsdense vector embeddingscross encoder rerankingsemantic similarity scoringembedding models retrievalsparse embeddings