stuff stuff

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+.DS_Store
+work

embeddings.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c78d4b65edb30b193dc6d8aa8a1f9fb90d3b8cf07ced05070fbcb74f4618f7a
+size 64409216

handler.py

@@ -0,0 +1,26 @@
+from typing import Dict, List, Any
+from sentence_transformers import SentenceTransformer
+import pandas as pd
+import numpy as np
+import os
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        self.model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+        self.embeddings = np.load(os.path.join(path, "embeddings.npy"))
+        self.spotify = pd.read_csv(os.path.join(path, "spotify.csv"))
+
+    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
+        """
+        input_embedding = self.model.encode(data["inputs"])
+        cos_score = self.embeddings @ input_embedding
+        top_10 = cos_score.argsort()[-10:][::-1]
+        return self.spotify.iloc[top_10].to_dict(orient="records")

spotify.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32167542d556bd066374acb61c72f656ed78f60150889e1abdfb210e0b43f2cd
+size 9745265