fn_registry/python/functions/embedding/embedding_encode.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_encode	function	py	infra	1.0.0	impure	def embedding_encode(model: SentenceTransformer, texts: list, mode: str = 'document') -> list	Genera embeddings normalizados para textos. Aplica prefijos e5 automaticamente segun mode (document/query).	embedding encode e5 multilingual python	embedding_load_model_py_infra			false	error_go_core	sentence_transformers	false			python/functions/embedding/model.py

Ejemplo

model = embedding_load_model(".local/models/e5-small")

# Indexar documentos
doc_embs = embedding_encode(model, ["La IA transforma la industria", "Python es versatil"], mode="document")

# Buscar
query_embs = embedding_encode(model, ["¿Que es machine learning?"], mode="query")

Notas

mode="document" agrega prefijo "passage: ", mode="query" agrega "query: ". Estos prefijos son requeridos por modelos e5 para retrieval optimo. Los embeddings retornados son float32 normalizados (norma L2 = 1). Para e5-small la dimension es 384. Throughput ~1900 docs/s en CPU.