import gradio as gr
from AinaTheme import AinaGradioTheme
from transformers import pipeline
import gradio as gr

ner_pipeline = pipeline("token-classification", model="projecte-aina/multiner_ceil",aggregation_strategy="first")

def ner(text):
    output = ner_pipeline(text)
    return {"text": text, "entities": output}    

demo = gr.Interface(
            ner,
            gr.Textbox(placeholder="Enter sentence here..."), 
            gr.HighlightedText(), 
            **AinaGradioTheme().get_kwargs(),
            flagging_options=None,
            article="""
            Multiner is a Named Entity Recognition (NER) model for the Catalan language fine-tuned from the [BERTa] model, a RoBERTa base model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers (check the BERTa model card for more details).
            It has been trained with a dataset (CEIL:  Catalan Entity Identification and Linking )  that contains 9 main types and 52 subtypes on all kinds of short texts, with almost 59K documents.
            Aquest resultat ha estat impulsat i finançat per la Generalitat de Catalunya mitjançant el projecte Aina (https://projecteaina.cat/).
            """)

demo.launch()