|
from typing import Dict, List, Any |
|
from optimum.onnxruntime import ORTModelForSequenceClassification |
|
from transformers import pipeline, AutoTokenizer |
|
|
|
|
|
class EndpointHandler(): |
|
def __init__(self, path=""): |
|
|
|
model = ORTModelForSequenceClassification.from_pretrained(path) |
|
tokenizer = AutoTokenizer.from_pretrained(path) |
|
|
|
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) |
|
|
|
|
|
if parameters is not None: |
|
prediction = self.pipeline(inputs, **parameters) |
|
else: |
|
prediction = self.pipeline(inputs) |
|
|
|
return prediction |
|
|
