Create handler.py

handler.py

@@ -0,0 +1,36 @@
+from typing import  Dict, List, Any
+
+from sentence_transformers import SentenceTransformer
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+
+        model_name = "all-MiniLM-L6-v2"
+
+        self.model = SentenceTransformer(
+            model_name,
+            backend="onnx",
+            model_kwargs={
+                "file_name": "model_O3.onnx",
+                "provider": "CUDAExecutionProvider",
+            }
+        )
+
+
+
+    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)
+
+        prediction = self.model.encode(inputs)
+
+        return prediction.tolist()