File size: 1,430 Bytes
0c86405
d4347a5
 
f1a16dd
0c86405
 
 
d4347a5
 
 
 
 
0c86405
 
 
d4347a5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
from typing import  Dict, List, Any
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline, AutoTokenizer


class EndpointHandler():
    def __init__(self, path=""):
        # load the optimized model
        model = ORTModelForSequenceClassification.from_pretrained(path)
        tokenizer = AutoTokenizer.from_pretrained(path)
        # create inference pipeline
        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)


    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.
        """
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # pass inputs with all kwargs in data
        if parameters is not None:
            prediction = self.pipeline(inputs, **parameters)
        else:
            prediction = self.pipeline(inputs)
        # postprocess the prediction
        return prediction