Update app.py

app.py

@@ -2,101 +2,99 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("urchade/gliner_multi-v2.1")
+model = GLiNER.from_pretrained("urchade/gliner_multi_pii-v1")
 
 examples = [
  [
- "Libretto by Marius Petipa, based on the 1822 novella ``Trilby, ou Le Lutin d'Argail`` by Charles Nodier, first presented by the Ballet of the Moscow Imperial Bolshoi Theatre on January 25/February 6 (Julian/Gregorian calendar dates), 1870, in Moscow with Polina Karpakova as Trilby and Ludiia Geiten as Miranda and restaged by Petipa for the Imperial Ballet at the Imperial Bolshoi Kamenny Theatre on January 17–29, 1871 in St. Petersburg with Adèle Grantzow as Trilby and Lev Ivanov as Count Leopold.",
- "person, book, location, date, actor, character",
- 0.3,
- True,
+ "Pierre Dubois, résident de Paris, a fondé sa propre entreprise, Le Petit Café, située au 15 Rue de la Paix. Son numéro d'entreprise est FR-987654321-1, et il utilise le compte bancaire 9876543210 pour les transactions.",
+ "person, organization, address, company registration number, bank account number",
+ 0.5,
+ False,
  ],
  [
- """
-* Data Scientist, Data Analyst, or Data Engineer with 1+ years of experience.
-* Experience with technologies such as Docker, Kubernetes, or Kubeflow
-* Machine Learning experience preferred
-* Experience with programming languages such as Python, C++, or SQL preferred
-* Experience with technologies such as Databricks, Qlik, TensorFlow, PyTorch, Python, Dash, Pandas, or NumPy preferred
-* BA or BS degree
-* Active Secret OR Active Top Secret or Active TS/SCI clearance
-""",
- "software package, programing language, software tool, degree, job title",
- 0.3,
+ "Leticia Ramírez, una habitante de Barcelona, tiene una cita médica programada en el Hospital General de Cataluña, situado en 10 Calle de los Ángeles. Su número de la seguridad social es ES-123456789-A y su grupo sanguíneo es AB+.",
+ "person, location, address, social security number, blood type",
+ 0.5,
  False,
  ],
  [
- "However, both models lack other frequent DM symptoms including the fibre-type dependent atrophy, myotonia, cataract and male-infertility.",
- "disease, symptom",
- 0.3,
+ "John Smith, from London, teaches mathematics at Royal Academy located at 25 King’s Road. His employee ID is UK-987654-321 and he has been working there since 2015.",
+ "person, profession, organization, address, employee ID number",
+ 0.5,
  False,
  ],
  [
- "Synergy between signal transduction pathways is obligatory for expression of c-fos in B and T cell lines: implication for c-fos control via surface immunoglobulin and T cell antigen receptors.",
- "DNA, RNA, cell line, cell type, protein",
- 0.3,
+ "In Frankfurt, Claudia Weber frequently visits her local bank branch, Deutsche Bank, at 48 Hauptstraße. Her account number is DE-1234567890123456, used primarily for her mortgage payments.",
+ "person, location, address, bank account number",
+ 0.5,
  False,
  ],
  [
- "The choice of the encoder and decoder modules of dnpg can be quite flexible, for instance long short term memory networks (lstm) or convolutional neural network (cnn).",
- "short acronym, long acronym",
- 0.3,
+ "Marta Rossi, residente a Roma, ha acquistato un appartamento al 123 Via Condotti. Il numero di registrazione della proprietà è IT-654321-2018 e il mutuo è gestito tramite la Banca d'Italia con numero di conto 3216549870.",
+ "person, address, property registration number, bank account number",
+ 0.5,
  False,
  ],
  [
- "Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.",
- "person, company, location, airplane",
- 0.3,
- True,
+ "Paulo Coelho, um turista do Brasil, fez um seguro de viagem com a empresa Seguros PT antes de sua viagem para Lisboa. O número da apólice é BR-987654321-123 e inclui cobertura médica.",
+ "person, nationality, company, insurance policy number, coverage",
+ 0.5,
+ False,
  ],
  [
- "Feldman is a contributor to NBC Sports Boston's ``State of the Revs`` and ``Revolution Postgame Live`` programs as well as to 98.5 the SportsHub, SiriusXM FC's MLS coverage and to other New England and national radio outlets and podcasts.",
- "person, company, location",
- 0.3,
+ "Julia Fischer, eine Kundin aus München, hat bei der BayWa AG, einem großen Anbieter von Baustoffen mit Sitz am 77 Industriestraße, einen Kredit aufgenommen. Die Kreditnummer lautet DE-12345678.",
+ "person, city, organization, address, loan number",
+ 0.5,
  False,
  ],
  [
- "On 25 July 1948, on the 39th anniversary of Bleriot's crossing of the English Channel, the Type 618 Nene-Viking flew Heathrow to Paris (Villacoublay) in the morning carrying letters to Bleriot's widow and son (secretary of the FAI), who met it at the airport.",
- "date, location, person, organization",
- 0.3,
+ "Carlos Sánchez, profesor en la Universidad de Madrid, reside en el 5 Calle de Alcalá. Su número de identificación de profesor es ES-192837465 y tiene un doctorado en filosofía.",
+ "person, profession, address, teacher ID number, degree",
+ 0.5,
  False,
  ],
  [
- "Leo & Ian won the 1962 Bathurst Six Hour Classic at Mount Panorama driving a Daimler SP250 sports car, (that year the 500 mile race for touring cars were held at Phillip Island)",
- "person, date, location, organization, competition",
- 0.3,
+ "Sophie Dupont, une journaliste française, travaille pour Le Monde, basé au 33 rue des Écoles à Paris. Son numéro d'identification de presse est FR-75649023.",
+ "person, profession, organization, address, press ID number",
+ 0.5,
  False,
  ],
  [
- "The Shore Line route of the CNS & M until 1955 served, from south to north, the Illinois communities of Chicago, Evanston, Wilmette, Kenilworth, Winnetka, Glencoe, Highland Park, Highwood, Fort Sheridan, Lake Forest, Lake Bluff, North Chicago, Waukegan, Zion, and Winthrop Harbor as well as Kenosha, Racine, and Milwaukee (the ``KRM'') in Wisconsin.",
- "location, organization, date",
- 0.3,
+ "Manuel Oliveira, um agricultor em Porto, possui uma grande plantação de vinhas na Rua da Estrada, 120. O número de registro agrícola é PT-5678912345.",
+ "person, profession, address, agricultural registration number",
+ 0.5,
  False,
  ],
  [
- "Comet C/2006 M4 (SWAN) is a non-periodic comet discovered in late June 2006 by Robert D. Matson of Irvine, California and Michael Mattiazzo of Adelaide, South Australia in publicly available images of the Solar and Heliospheric Observatory (SOHO).",
- "person, organization, date, location",
- 0.3,
+ "Elisa Müller, eine Künstlerin aus Berlin, hat ihre neueste Skulptur im öffentlichen Park am Alexanderplatz ausgestellt. Ihre Künstlernummer lautet DE-112233445.",
+ "person, profession, location, artist ID number",
+ 0.5,
  False,
  ],
  [
- "From November 29, 2011 to March 31, 2012, Karimloo returned to ``Les Misérables`` to play the lead role of Jean Valjean at The Queen's Theatre, London, for which he won the 2013 Theatregoers' Choice Award for Best Takeover in a Role.",
- "person, actor, award, date, location",
- 0.3,
+ "Federico García, un jugador de fútbol de Sevilla, ha firmado un contrato de tres años con el club Real Betis. Su número de licencia deportiva es ES-9876543210.",
+ "person, profession, organization, sports license number",
+ 0.5,
  False,
  ],
  [
- "A Mexicali health clinic supported by former Baja California gubernatorial candidate Enrique Acosta Fregoso (PRI) was closed on June 15 after selling a supposed COVID-19 ``cure'' for between MXN $10,000 and $50,000.",
- "location, organization, person, date, currency",
- 0.3,
+ "Sarah White, a London-based actress, will be performing in 'Hamlet' at the Globe Theatre located at 21 New Globe Walk. Her Equity membership number is UK-1234567.",
+ "person, profession, location, address, membership number",
+ 0.5,
  False,
  ],
  [
- "Built in 1793, it was the home of Mary Young Pickersgill when she moved to Baltimore in 1806 and the location where she later sewed the ``Star Spangled Banner'', in 1813, the huge out-sized garrison flag that flew over Fort McHenry at Whetstone Point in Baltimore Harbor in the summer of 1814 during the British Royal Navy attack in the Battle of Baltimore during the War of 1812.",
- "date, person, location, organization, event, flag",
- 0.3,
+ "Ricardo Mello, engenheiro civil, trabalha na construção da nova barragem no Rio Douro, Portugal. Seu número de registro profissional é PT-987654321.",
+ "person, profession, project location, professional registration number",
+ 0.5,
  False,
  ],
+ [
+ "Giuseppe Conti, un cliente di Milano, ha fatto un acquisto presso il negozio La Rinascente situato in Piazza Duomo. Il numero della sua carta di credito è IT-4567891234567891.",
+ "person, location, address, credit card number",
+ 0.5,
+ False,
+ ]
 ]
 
 
@@ -153,14 +151,13 @@ with gr.Blocks(title="GLiNER-M-v2.1") as demo:
  '''
 from gliner import GLiNER
 
-model = GLiNER.from_pretrained("urchade/gliner_mediumv2.1")
+model = GLiNER.from_pretrained("urchade/gliner_multi_pii-v1")
 
 text = """
-Cristiano Ronaldo dos Santos Aveiro (Portuguese pronunciation: [kɾiʃˈtjɐnu ʁɔˈnaldu]; born 5 February 1985) is a Portuguese professional footballer who plays as a forward for and captains both Saudi Pro League club Al Nassr and the Portugal national team. Widely regarded as one of the greatest players of all time, Ronaldo has won five Ballon d'Or awards,[note 3] a record three UEFA Men's Player of the Year Awards, and four European Golden Shoes, the most by a European player. He has won 33 trophies in his career, including seven league titles, five UEFA Champions Leagues, the UEFA European Championship and the UEFA Nations League. Ronaldo holds the records for most appearances (183), goals (140) and assists (42) in the Champions League, goals in the European Championship (14), international goals (128) and international appearances (205). He is one of the few players to have made over 1,200 professional career appearances, the most by an outfield player, and has scored over 850 official senior career goals for club and country, making him the top goalscorer of all time.
+Harilala Rasoanaivo, un homme d'affaires local d'Antananarivo, a enregistré une nouvelle société nommée "Rasoanaivo Enterprises" au Lot II M 92 Antohomadinika. Son numéro est le +261 32 22 345 67, et son adresse électronique est harilala.[email protected]. Il a fourni son numéro de sécu 501-02-1234 pour l'enregistrement.
 """
 
-labels = ["person", "award", "date", "competitions", "teams"]
-
+labels = ["work", "booking number", "personally identifiable information", "driver licence", "person", "book", "full address", "company", "actor", "character", "email", "passport number", "Social Security Number", "phone number"]
 entities = model.predict_entities(text, labels)
 
 for entity in entities:
@@ -170,18 +167,12 @@ for entity in entities:
  )
  gr.Code(
  """
-Cristiano Ronaldo dos Santos Aveiro => person
-5 February 1985 => date
-Al Nassr => teams
-Portugal national team => teams
-Ballon d'Or => award
-UEFA Men's Player of the Year Awards => award
-European Golden Shoes => award
-UEFA Champions Leagues => competitions
-UEFA European Championship => competitions
-UEFA Nations League => competitions
-Champions League => competitions
-European Championship => competitions
+Harilala Rasoanaivo => person
+Rasoanaivo Enterprises => company
+Lot II M 92 Antohomadinika => full address
++261 32 22 345 67 => phone number
+[email protected] => email
+501-02-1234 => Social Security Number
  """
  )