Return embeddings as array instead of nested in JSON

handler.py

@@ -17,7 +17,7 @@ class EndpointHandler():
         self.model = ORTModelForFeatureExtraction.from_pretrained(path, file_name="model-quantized.onnx")
         self.tokenizer = AutoTokenizer.from_pretrained(path)
 
-    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+    def __call__(self, data: Any) -> List[List[float]]:
         """
         Args:
             data (:obj:):
@@ -36,4 +36,4 @@ class EndpointHandler():
         # Normalize embeddings
         sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
         # postprocess the prediction
-        return {"embeddings": sentence_embeddings.tolist()}
+        return sentence_embeddings.tolist()