fn_registry/python/functions/embedding/embedding_store_usearch.md

name, kind, lang, domain, version, purity, signature, description, tags, uses_functions, uses_types, returns, returns_optional, error_type, imports, 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	tested	tests	test_file_path	file_path
embedding_store_usearch	function	py	infra	1.0.0	impure	def embedding_store_usearch(path: str, ids: list, embeddings: list, dim: int = 384) -> int	Crea indice USearch con embeddings y lo persiste a archivo. Busqueda sub-milisegundo.	embedding usearch vector store ann python				false	error_go_core	usearch numpy	false			python/functions/embedding/usearch_store.py

Ejemplo

model = embedding_load_model(".local/models/e5-small")
docs = ["La IA transforma la industria", "Python es versatil"]
embs = embedding_encode(model, docs, mode="document")

n = embedding_store_usearch("docs.usearch", [0, 1], embs)
# n = 2

Notas

USearch usa HNSW (approximate nearest neighbors). Para 50k vectores dim=384: ~80 MB en disco, busqueda ~0.13ms/query (150x mas rapido que sqlite-vec). El tradeoff es que no soporta metadata nativa — usar junto con SQLite para metadata. Sobreescribe el archivo si ya existe.