egutierrez
faac610745
Extrae al registry funciones del proyecto interno footprint_aurgi: - core (6): slugify_ascii, normalize_for_join, cp_provincia_es, infer_provincia_from_cp, safe_read_csv_fallback, csv_to_parquet_duckdb - geo puras (7): haversine_km, point_in_ring, point_in_polygon, point_in_polygons_bbox, polygon_bbox, extent_with_padding, distance_bucket - geo I/O (4): load_geojson_polygons, load_boundary_gdf, add_basemap_osm, add_basemap_with_timeout - valhalla client (4): valhalla_route, valhalla_isochrone, valhalla_isochrones_async, valhalla_matrix_1_to_n - datascience stats (7): trimmed_mean, geometric_mean, detect_distribution_type, best_central_tendency, summary_stats, kde_density_levels, alpha_shape_concave_hull - datascience fuzzy (3): fuzzy_merge_adaptive (rapidfuzz), words_to_dataset, remove_words_from_column - datascience viz (2): plot_kde_2d, plot_heatmap_log - infra (4): compress_pdf_ghostscript, render_table_page_pdfpages, add_header_logo, osm2pgsql_ingest - pipelines (4): setup_geo_stack_docker, compute_centers_reachability, generate_isochrones_by_zone, count_points_per_zone - types geo (4): LonLat, BBox, IsochroneRequest, Centro Incluye: - apps/footprint_geo_stack/ (PostGIS + Martin + Valhalla via docker-compose) - 131/132 tests pasan (1 skip esperado: osm2pgsql en PATH) - Issue tracker dev/issues/0052-footprint-aurgi-extraction.md - Atribucion uniforme: source_repo internal:footprint_aurgi, source_license internal-aurgi - Build con 9 agentes en paralelo (8 wave 1 + 1 wave 2 pipelines) Tambien commitea trabajo previo no commiteado: aggregate_extraction_results, chunk_with_overlap, clean_pdf_text, merge_entity_aliases, extract_graph_gliner2, extract_relations_mrebel, extract_triples_spacy_es, gliner2/mrebel/marianmt/rebel/spacy_es load_model, parse_rebel_output, translate_es_to_en, issue 0050/0051. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
63 lines
1.8 KiB
Python
63 lines
1.8 KiB
Python
"""Carga (y cachea) un modelo GLiNER2 (NER+RE joint en una sola pasada).
|
|
|
|
LICENSE: Apache 2.0 — uso comercial permitido.
|
|
Modelo por defecto: fastino/gliner2-large-v1
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
# Cache global: (model_name, device) -> instancia GLiNER2
|
|
_MODEL_CACHE: dict[tuple[str, str], Any] = {}
|
|
|
|
|
|
def _resolve_device(device: str) -> str:
|
|
"""Resuelve 'auto' a 'cuda' o 'cpu' segun disponibilidad de torch."""
|
|
if device != "auto":
|
|
return device
|
|
try:
|
|
import torch
|
|
except ImportError:
|
|
return "cpu"
|
|
return "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
|
|
def gliner2_load_model(
|
|
model_name: str = "fastino/gliner2-large-v1",
|
|
device: str = "auto",
|
|
) -> Any:
|
|
"""Load (and cache) a GLiNER2 model.
|
|
|
|
GLiNER2 extracts entities AND relations in a single forward pass using
|
|
a joint schema (entities + relation_labels). This is ~2x faster than
|
|
running GLiNER + GLiREL separately for co-occurring entities.
|
|
|
|
Returns model instance with .extract() and .create_schema() methods.
|
|
|
|
LICENSE: Apache 2.0 — commercial use OK.
|
|
|
|
Args:
|
|
model_name: HuggingFace Hub model ID. Default: fastino/gliner2-large-v1.
|
|
device: 'auto' uses CUDA if available, else CPU. 'cpu', 'cuda', 'cuda:N'.
|
|
|
|
Returns:
|
|
GLiNER2 instance cached by (model_name, device).
|
|
"""
|
|
resolved = _resolve_device(device)
|
|
key = (model_name, resolved)
|
|
if key in _MODEL_CACHE:
|
|
return _MODEL_CACHE[key]
|
|
|
|
from gliner2 import GLiNER2 # type: ignore[import]
|
|
|
|
m = GLiNER2.from_pretrained(model_name)
|
|
if hasattr(m, "to") and resolved != "cpu":
|
|
try:
|
|
m.to(resolved)
|
|
except Exception:
|
|
pass # Fallback to CPU silently
|
|
|
|
_MODEL_CACHE[key] = m
|
|
return m
|