Update handler.py

handler.py

@@ -13,11 +13,12 @@ class EndpointHandler():
 
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
-        inputs = data.get("inputs")
-        text = inputs.get("text")
-        imageData = inputs.get("image")
-        image = Image.open(BytesIO(base64.b64decode(imageData)))
+        url = data.get("inputs")
+        text = data.get("text")
+        image = Image.open(requests.get(url, stream=True).raw)
         inputs = self.processor(text=text, images=image, return_tensors="pt", padding=True)
         outputs = self.model(**inputs)
+        logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+        probs = logits_per_image.softmax(dim=1) 
         embeddings = outputs.image_embeds.detach().numpy().flatten().tolist()
         return { "embeddings": embeddings }