from typing import Dict, Union import sys sys.path.extend(["./GLiNER"]) from GLiNER.model import GLiNER import gradio as gr model = GLiNER.from_pretrained("urchade/gliner_multi") 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", True, ], [ "However, both models lack other frequent DM symptoms including the fibre-type dependent atrophy, myotonia, cataract and male-infertility.", "disease, symptom", False, ], [ "Napoléon Bonaparte (de son nom de baptême Napoleone Buonaparte), né le 15 août 1769 à Ajaccio et mort le 5 mai 1821 sur l'île de Sainte-Hélène, est un militaire et homme d'État français. Il est le premier empereur des Français du 18 mai 1804 au 6 avril 1814 et du 20 mars au 22 juin 1815, sous le nom de Napoléon Ier.", "person, book, location, date, job", 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", False, ], [ "Cette formalité est payante. L’article 739 du Code général des impôts précise que le montant des frais d’enregistrement est de 25€.", "texte de loi, montant financier, animal", True, ], [ "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", False, ], ] def ner(text, labels: str, nested_ner: bool) -> Dict[str, Union[str, int, float]]: labels = labels.split(",") return { "text": text, "entities": [ { "entity": entity["label"], "word": entity["text"], "start": entity["start"], "end": entity["end"], "score": 0, } for entity in model.predict_entities(text, labels, flat_ner=not nested_ner) ], } with gr.Blocks(title="GLiNER-base") as demo: gr.Markdown( """ # GLiNER-Multi GLiNER is a Named Entity Recognition (NER) model capable of identifying any entity type using a bidirectional transformer encoder (BERT-like). It provides a practical alternative to traditional NER models, which are limited to predefined entities, and Large Language Models (LLMs) that, despite their flexibility, are costly and large for resource-constrained scenarios. ## Links * Paper: https://arxiv.org/abs/2311.08526 * Repository: https://github.com/urchade/GLiNER """ ) with gr.Accordion("How to run this model locally", open=False): gr.Markdown( """ ## Installation To use this model, you must download the GLiNER repository and install its dependencies: ``` !git clone https://github.com/urchade/GLiNER.git %cd GLiNER !pip install -r requirements.txt ``` ## Usage Once you've downloaded the GLiNER repository, you can import the GLiNER class from the `model` file. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`. """ ) gr.Code( ''' from model import GLiNER model = GLiNER.from_pretrained("urchade/gliner_multi") 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. """ labels = ["person", "award", "date", "competitions", "teams"] entities = model.predict_entities(text, labels) for entity in entities: print(entity["text"], "=>", entity["label"]) ''', language="python", ) 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 """ ) input_text = gr.Textbox( value=examples[0][0], label="Text input", placeholder="Enter your text here" ) with gr.Row() as row: labels = gr.Textbox( value=examples[0][1], label="Labels", placeholder="Enter your labels here (comma separated)", scale=1, ) nested_ner = gr.Checkbox( value=examples[0][2], label="Nested NER", info="Allow for nested NER?", scale=0, ) output = gr.HighlightedText(label="Predicted Entities") submit_btn = gr.Button("Submit") examples = gr.Examples( examples, fn=ner, inputs=[input_text, labels, nested_ner], outputs=output, cache_examples=True, ) # Submitting input_text.submit(fn=ner, inputs=[input_text, labels, nested_ner], outputs=output) submit_btn.click(fn=ner, inputs=[input_text, labels, nested_ner], outputs=output) demo.queue() demo.launch(debug=True)