fn_registry/python/functions/datascience/extract_graph_gliner2.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, notes

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	notes
extract_graph_gliner2	function	py	datascience	1.0.0	impure	def extract_graph_gliner2(text: str, entity_labels: list[str], relation_labels: list | dict, model: Any, threshold: float = 0.3, include_confidence: bool = False) -> dict	Extrae entidades + relaciones en una sola pasada con GLiNER2. Wrapper de alto nivel: construye schema, ejecuta extraccion, normaliza a dict plano. No aplica post-filtrado ni coreference.	gliner2 ner relation-extraction nlp extraction graph zero-shot datascience python apache2	gliner2_load_model_py_datascience			false	error_go_core	time typing.Any	name desc text Texto a analizar. Recomendado hasta 1500 chars (pre-chunkeado con chunk_with_overlap). Textos mas largos degradan el recall de GLiNER2. name desc entity_labels Lista de strings con los tipos de entidad en minusculas snake_case. E.g. ['person', 'organization', 'location']. Labels en snake_case mejoran el recall segun notebook 08. name desc relation_labels Lista de strings o dict {label: description} con los tipos de relacion. E.g. ['works_at', 'ceo_of'] o {'works_at': 'person works at an organization'}. name desc model Instancia GLiNER2 cargada con gliner2_load_model. Inyectada por el caller (no se carga aqui). name desc threshold Umbral de confianza entre 0 y 1. 0.3 validado empiricamente en notebook 04 (gliner_glirel_tuning). Valores mas bajos = mas recall, mas ruido. name desc include_confidence Si True, GLiNER2 devuelve scores internos por entidad y relacion. False por defecto para output mas limpio.	Dict con tres campos: 'entities' -> {type: [name, ...]}, 'relation_extraction' -> {rel_type: [(head, tail), ...]}, 'elapsed_s' -> float. Compatible con aggregate_extraction_results.	true	output tiene claves entities relation_extraction elapsed_s stub model retorna shape correcto	python/functions/datascience/tests/test_extract_graph_gliner2.py	python/functions/datascience/extract_graph_gliner2.py	LICENSE: GLiNER2 (fastino/gliner2-large-v1) es Apache 2.0 — uso comercial OK. impure: invoca inferencia del modelo (side effect computacional + tiempo variable). El model se inyecta externamente para permitir cache y reutilizacion entre llamadas. Para textos largos usar chunk_with_overlap antes y llamar esta funcion por chunk, luego agregar con aggregate_extraction_results.

Ejemplo

from datascience.gliner2_load_model import gliner2_load_model
from datascience.extract_graph_gliner2 import extract_graph_gliner2

model = gliner2_load_model(device="auto")

result = extract_graph_gliner2(
    text="Carlos Torres es presidente de BBVA, con sede en Bilbao.",
    entity_labels=["person", "organization", "location"],
    relation_labels=["president_of", "headquartered_in"],
    model=model,
    threshold=0.3,
)
# result["entities"]           -> {"person": ["Carlos Torres"], ...}
# result["relation_extraction"]-> {"president_of": [("Carlos Torres", "BBVA")]}
# result["elapsed_s"]          -> 0.234