from typing import Dict, Union from gliner import GLiNER import gradio as gr model = GLiNER.from_pretrained("placingholocaust/gliner_small-v2.1-holocaust") examples = [ [ "Okay. So now it's spring of '44? A: ‘4, And she says, You're going to go to Brzezinka . I said, What is Brzezinka ? She said, It's a crematorium and the gas chamber . They have a half a million Hungarian Jews are coming in. That's when the time they -- and they need people to select. We do not select the people to -- who die or not. The women fold the clothes and look for jewelry and make packages to send it to Germany.", "dlf, populated place, country, region, interior space, env feature, building, spatial object.", 0.3, True, ] ] def ner( text, labels: str, threshold: float, 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, threshold=threshold ) ], } with gr.Blocks(title="GLiNER-M-v2.1") as demo: gr.Markdown("# GliNER model for Holocaust NER.") with gr.Accordion("About this model.", open=False): gr.Markdown( """ # GLiNER-base 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 * Original GliNER model: https://huggingface.co/urchade/gliner_small-v2.1 * Finetuned GliNER model: https://huggingface.co/placingholocaust/gliner_small-v2.1-holocaust * Finetuned with this data: https://huggingface.co/datasets/placingholocaust/spacy-project * 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 install the GLiNER Python library: # ``` # !pip install gliner # ``` # ## Usage # Once you've downloaded the GLiNER library, you can import the GLiNER class. You can then load this model using `GLiNER.from_pretrained` and predict entities with `predict_entities`. # """ # ) # gr.Code( # ''' # from gliner import GLiNER # model = GLiNER.from_pretrained("urchade/gliner_mediumv2.1") # 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=2, ) threshold = gr.Slider( 0, 1, value=0.3, step=0.01, label="Threshold", info="Lower the threshold to increase how many entities get predicted.", 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, threshold, nested_ner], outputs=output, cache_examples=True, ) # Submitting input_text.submit( fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output ) labels.submit( fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output ) threshold.release( fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output ) submit_btn.click( fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output ) nested_ner.change( fn=ner, inputs=[input_text, labels, threshold, nested_ner], outputs=output ) demo.queue() demo.launch(debug=True)