Stepanov

#!pip install gliner -U

from gliner import GLiNER

model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5")

text = """
Microsoft was founded by Bill Gates and Paul Allen on April 4, 1975 to develop and sell BASIC interpreters for the Altair 8800. 
"""

labels = ["founder", "computer", "software", "position", "date"]

entities = model.predict_entities(text, labels)

for entity in entities:
    print(entity["text"], "=>", entity["label"])

pip install gliner

from gliner import GLiNER

model = GLiNER.from_pretrained("knowledgator/gliner_small-v2.1")

prompt = """Find all positive aspects about the product:\n"""
text = """
I recently purchased the Sony WH-1000XM4 Wireless Noise-Canceling Headphones from Amazon and I must say, I'm thoroughly impressed. The package arrived in New York within 2 days, thanks to Amazon Prime's expedited shipping.

The headphones themselves are remarkable. The noise-canceling feature works like a charm in the bustling city environment, and the 30-hour battery life means I don't have to charge them every day. Connecting them to my Samsung Galaxy S21 was a breeze, and the sound quality is second to none.
I also appreciated the customer service from Amazon when I had a question about the warranty. They responded within an hour and provided all the information I needed.
However, the headphones did not come with a hard case, which was listed in the product description. I contacted Amazon, and they offered a 10% discount on my next purchase as an apology.
Overall, I'd give these headphones a 4.5/5 rating and highly recommend them to anyone looking for top-notch quality in both product and service.
"""
input_ = prompt+text

labels = ["match"]

matches = model.predict_entities(input_, labels)

for match in matches:
    print(match["text"], "=>", match["score"])

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". """
})

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". """
})