Update app.py

app.py

@@ -6,7 +6,9 @@ from datasets import load_dataset
 from datasets import Features
 from datasets import Value
 from datasets import Dataset
-
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import os
 
 Secret_token = os.getenv('HF_token')
 
@@ -30,5 +32,10 @@ cols_to_use = df.columns.difference(matn_info.columns)
 joined_df = matn_info.merge(df[cols_to_use], left_index=True, right_on='__index_level_0__')
 df = joined_df.copy()
 
+model = SentenceTransformer('FDSRashid/QulBERT', token=Secret_token)
+
 
+def find_most_similar_matn(text, n):
+    embed_text = model.encode(araby.strip_diacritics(text))
+