first

.gitignore

@@ -0,0 +1,2 @@
+.ipynb_checkpoints
+compute.ipynb

artwork_urls.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9f605c3852001ad53e4f7324e6f56ae88a2786ee40e19d10bec950d6192cd3
+size 2152944

embeddings.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e07a3d10e239135feaa71e868c447e6e2bed382d37128da9d525a2cf0855f7c
+size 89392256

handler.py

@@ -0,0 +1,31 @@
+from typing import Dict, List, Any
+from transformers import CLIPTokenizer, CLIPModel
+import numpy as np
+import os
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        self.model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
+        self.tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
+
+        self.artwork_urls = np.load(os.path.join(path, "artwork_urls.npy"), allow_pickle=True)
+        self.embeddings = np.load(os.path.join(path, "embeddings.npy"), allow_pickle=True)
+
+    def __call__(self, data: Dict[str, Any]) -> List[float]:
+        """
+         data args:
+              inputs (:obj: `str` | `PIL.Image` | `np.array`)
+              kwargs
+        Return:
+              A :obj:`list` | `dict`: will be serialized and returned
+        """
+        inputs = self.tokenizer(data["inputs"], padding=True, return_tensors="pt")
+        text_features = self.model.get_text_features(**inputs)
+        input_embedding = text_features[0]
+        input_embedding = input_embedding / np.linalg.norm(input_embedding)
+
+        cos_score = self.embeddings @ input_embedding
+        top_10 = cos_score.argsort()[-100:][::-1]
+
+        return self.artwork_urls[top_10].tolist()

requirements.txt

@@ -0,0 +1,2 @@
+transformers==4.21.1
+numpy==1.23.4