Create handler.py

handler.py

@@ -0,0 +1,24 @@
+from typing import Dict, List, Any
+from optimum.pipeline import pipeline
+from transformers import AutoTokenizer
+from optimum import ORTModelForSeq2SeqLM
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        tokenizer = AutoTokenizer.from_pretrained(path)
+        model = ORTModelForSeq2SeqLM.from_pretrained(path)
+        self.pipeline = pipeline("summarization",model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """
+       data args:
+            inputs (:obj: `str`)
+      Return:
+            A :obj:`list` | `dict`: will be serialized and returned
+        """
+        # get inputs
+        inputs = data.pop("inputs",data)
+
+        # run normal prediction
+        return self.pipeline(inputs)

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+optimum