|
from typing import Dict, List, Any |
|
from transformers import AutoModel, AutoTokenizer |
|
|
|
|
|
class EndpointHandler(): |
|
def __init__(self, path=""): |
|
self.tokenizer = AutoTokenizer.from_pretrained("Wellcome/WellcomeBertMesh") |
|
self.model = AutoModel.from_pretrained("Wellcome/WellcomeBertMesh", trust_remote_code=True) |
|
|
|
def __call__(self, data: Any) -> List[List[Dict[str, float]]]: |
|
""" |
|
Args: |
|
data (:obj:): |
|
includes the input data and the parameters for the inference. |
|
Return: |
|
A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing : |
|
- "label": A string representing what the label/class is. There can be multiple labels. |
|
- "score": A score between 0 and 1 describing how confident the model is for this label/class. |
|
""" |
|
text = data.pop("inputs", data) |
|
inputs = self.tokenizer(text, padding="max_length") |
|
preds = self.model(input_ids=[inputs["input_ids"]]) |
|
|
|
id2label = self.model.config.id2label |
|
|
|
prediction = [ |
|
{"label": id2label[label_id], "score": p} |
|
for label_id, p in enumerate(preds[0].tolist()) if p > 0.5 |
|
] |
|
return prediction |
|
|