fn_registry/python/functions/embedding/embedding_search_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_search_usearch	function	py	infra	1.0.0	impure	def embedding_search_usearch(path: str, query_embedding: list, k: int = 10, dim: int = 384) -> list	Busca los k vecinos mas cercanos en indice USearch persistido. Busqueda sub-milisegundo.	embedding usearch vector search retrieval ann python				false	error_go_core	usearch numpy	false			python/functions/embedding/usearch_store.py

Ejemplo

model = embedding_load_model(".local/models/e5-small")
q_emb = embedding_encode(model, ["¿Que es machine learning?"], mode="query")[0]

results = embedding_search_usearch("docs.usearch", q_emb, k=5)
# [{"key": 0, "distance": 0.82}, {"key": 1, "distance": 0.65}, ...]

Notas

Carga el indice completo a RAM antes de buscar. Cold start ~190ms para 50k vectores. Busqueda aproximada (HNSW) — puede no encontrar el vecino exacto pero es 150x mas rapido que brute-force. Distance es inner product (mayor = mas similar, al reves que sqlite-vec).