docker_images/common/app/pipelines/token_classification.py

from typing import Any, Dict, List

from app.pipelines import Pipeline


class TokenClassificationPipeline(Pipeline):
    def __init__(
        self,
        model_id: str,
    ):
        # IMPLEMENT_THIS
        # Preload all the elements you are going to need at inference.
        # For instance your model, processors, tokenizer that might be needed.
        # This function is only called once, so do all the heavy processing I/O here
        raise NotImplementedError(
            "Please implement TokenClassificationPipeline __init__ function"
        )

    def __call__(self, inputs: str) -> List[Dict[str, Any]]:
        """
        Args:
            inputs (:obj:`str`):
                a string containing some text
        Return:
            A :obj:`list`:. The object returned should be like [{"entity_group": "XXX", "word": "some word", "start": 3, "end": 6, "score": 0.82}] containing :
                - "entity_group": A string representing what the entity is.
                - "word": A rubstring of the original string that was detected as an entity.
                - "start": the offset within `input` leading to `answer`. context[start:stop] == word
                - "end": the ending offset within `input` leading to `answer`. context[start:stop] === word
                - "score": A score between 0 and 1 describing how confident the model is for this entity.
        """
        # IMPLEMENT_THIS
        raise NotImplementedError(
            "Please implement TokenClassificationPipeline __call__ function"
        )