fn_registry/python/functions/embedding/embedding_save_model.md

name, kind, lang, domain, version, purity, signature, description, tags, uses_functions, uses_types, returns, returns_optional, error_type, imports, params, output, tested, tests, test_file_path, file_path

name	kind	lang	domain	version	purity	signature	description	tags	uses_functions	uses_types	returns	returns_optional	error_type	imports	params	output	tested	tests	test_file_path	file_path
embedding_save_model	function	py	infra	1.0.0	impure	def embedding_save_model(model_id: str, path: str) -> str	Descarga modelo de embeddings de HuggingFace y lo guarda en path local para carga rapida sin red.	embedding model save huggingface e5 python pendiente-usar				false	error_go_core	sentence_transformers	name desc model_id identificador de modelo en HuggingFace (ej: intfloat/multilingual-e5-small) name desc path ruta local donde guardar el modelo descargado	string: ruta absoluta donde se guardó el modelo	false			python/functions/embedding/model.py

Ejemplo

path = embedding_save_model("intfloat/multilingual-e5-small", ".local/models/e5-small")
# path = "$HOME/fn_registry/.local/models/e5-small"

Notas

El modelo se guarda en formato sentence-transformers (safetensors + tokenizer). Para multilingual-e5-small ocupa ~465 MB en disco. Carga local es ~2.3x mas rapida que desde HF cache.