misc/py-sentence-transformers: New port: PyTorch: Ready to use implementations of generative models

misc/Makefile

@@ -546,6 +546,7 @@
     SUBDIR += py-schedulefree
     SUBDIR += py-scikit-fusion
     SUBDIR += py-scikit-quant
+    SUBDIR += py-sentence-transformers
     SUBDIR += py-serverfiles
     SUBDIR += py-shap2
     SUBDIR += py-shell-gpt

misc/py-sentence-transformers/Makefile

@@ -0,0 +1,38 @@
+PORTNAME=	sentence-transformers
+DISTVERSION=	5.1.0
+CATEGORIES=	misc # machine-learning
+MASTER_SITES=	PYPI
+PKGNAMEPREFIX=	${PYTHON_PKGNAMEPREFIX}
+DISTNAME=	${PORTNAME:S/-/_/}-${PORTVERSION}
+
+MAINTAINER=	yuri@FreeBSD.org
+COMMENT=	PyTorch: Ready to use implementations of generative models
+WWW=		https://www.sbert.net/ \
+		https://github.com/UKPLab/sentence-transformers/
+
+LICENSE=	APACHE20
+LICENSE_FILE=	${WRKSRC}/LICENSE
+
+BUILD_DEPENDS=	${PY_SETUPTOOLS} \
+		${PYTHON_PKGNAMEPREFIX}wheel>0:devel/py-wheel@${PY_FLAVOR}
+RUN_DEPENDS=	${PYTHON_PKGNAMEPREFIX}huggingface-hub>=0.20.0:misc/py-huggingface-hub@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}pillow>0:graphics/py-pillow@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}pytorch>=1.11.0:misc/py-pytorch@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}scikit-learn>0:science/py-scikit-learn@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}scipy>0:science/py-scipy@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}tqdm>0:misc/py-tqdm@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}transformers>=4.41.0<5.0.0:misc/py-transformers@${PY_FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}typing-extensions>=4.5.0:devel/py-typing-extensions@${PY_FLAVOR}
+RUN_DEPENDS+=	${PYTHON_PKGNAMEPREFIX}tokenizers>0:textproc/py-tokenizers@${PY_FLAVOR}
+
+USES=		python
+USE_PYTHON=	pep517 autoplist pytest
+
+TEST_ENV=	${MAKE_ENV} PYTHONPATH=${STAGEDIR}${PYTHONPREFIX_SITELIBDIR}
+TEST_WRKSRC=	${WRKSRC}/tests
+
+NO_ARCH=	yes
+
+# tests fail to run, see https://github.com/UKPLab/sentence-transformers/issues/3520
+
+.include <bsd.port.mk>

misc/py-sentence-transformers/distinfo

@@ -0,0 +1,3 @@
+TIMESTAMP = 1758260582
+SHA256 (sentence_transformers-5.1.0.tar.gz) = 70c7630697cc1c64ffca328d6e8688430ebd134b3c2df03dc07cb3a016b04739
+SIZE (sentence_transformers-5.1.0.tar.gz) = 370745

misc/py-sentence-transformers/pkg-descr

@@ -0,0 +1,8 @@
+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 (quickstart), to
+calculate similarity scores using Cross-Encoder (a.k.a. reranker) models
+(quickstart) or to generate sparse embeddings using Sparse Encoder models
+(quickstart).
+This unlocks a wide range of applications, including semantic search, semantic
+textual similarity, and paraphrase mining.