ko-ko PRO

from utca.core import (
    AddData,
    RenameAttribute,
    Flush
)
from utca.implementation.predictors import (
    TokenSearcherPredictor, TokenSearcherPredictorConfig
)
from utca.implementation.tasks import (
    TokenSearcherNER,
    TokenSearcherNERPostprocessor,
)
predictor = TokenSearcherPredictor(
    TokenSearcherPredictorConfig(
        device="cuda:0",
        model="knowledgator/UTC-DeBERTa-base-v2"
    )
)
ner_task = TokenSearcherNER(
    predictor=predictor,
    postprocess=[TokenSearcherNERPostprocessor(
        threshold=0.5
    )]
)

ner_task = TokenSearcherNER()

pipeline = (        
    AddData({"labels": ["scientist", "university", "city"]})         
    | ner_task
    | Flush(keys=["labels"])
    | RenameAttribute("output", "entities")
)
res = pipeline.run({
    "text": """Dr. Paul Hammond, a renowned neurologist at Johns Hopkins University, has recently published a paper in the prestigious journal "Nature Neuroscience". """
})