app.py

import gradio as gr
from dataclasses import dataclass

from pytorch_ie.annotations import LabeledSpan
from pytorch_ie.auto import AutoPipeline
from pytorch_ie.core import AnnotationList, annotation_field
from pytorch_ie.documents import TextDocument

from spacy import displacy


@dataclass
class ExampleDocument(TextDocument):
    entities: AnnotationList[LabeledSpan] = annotation_field(target="text")


model_name_or_path = "leonhardhennig/copious_ner"

ner_pipeline = AutoPipeline.from_pretrained(model_name_or_path, device=-1, num_workers=0)


def predict(text):
    document = ExampleDocument(text)

    ner_pipeline(document)
    
    doc = {
        "text": document.text,
        "ents": [{
            "start": entity.start,
            "end": entity.end,
            "label": entity.label
        } for entity in sorted(document.entities.predictions, key=lambda e: e.start)],
        "title": None
    }

    html = displacy.render(doc, style="ent", page=True, manual=True, minify=True)
    html = (
        "<div style='max-width:100%; max-height:360px; overflow:auto'>"
        + html
        + "</div>"
    )
    
    return html


iface = gr.Interface(
    fn=predict,
    inputs=gr.inputs.Textbox(
        lines=5,
        default="The most valuable mother-of-pearl is obtained from four species; Pinctada maxima  P. margaritifera  Trochus niloticus and Turbo marmoratus.",
    ),
    outputs="html",
)
iface.launch()