Update app.py

app.py

@@ -16,7 +16,8 @@ def load_similarity_model(model_name='all-MiniLM-L6-v2'):
     return model
 
 # list of supported models
-supported_models = ['all-MiniLM-L6-v2', 'paraphrase-albert-small-v2', 'paraphrase-MiniLM-L3-v2', 'all-distilroberta-v1', 'all-mpnet-base-v2']
+supported_models = {'English': 'all-MiniLM-L6-v2', 'Multilingual': 'paraphrase-multilingual-MiniLM-L12-v2']
+#supported_models = ['English', 'Multilingual']
 
 # read the emoji df and extract the relevant columns
 emoji_df = pd.read_csv('EmojiCharts_unicodeorg.csv')[['name', 'codepoints']]
@@ -32,7 +33,7 @@ def encode_emoji(emoji):
     return emoji_text.encode().decode('unicode-escape')
 
 # find the top similar sentences
-def find_similar_sentences(query, target_sentences, n=5):
+def find_similar_sentences(query, target_sentences, n=2):
     # compute embeddings
     embeddings_query = model.encode([query], convert_to_tensor=True)
     embeddings_target = model.encode(target_sentences, convert_to_tensor=True)
@@ -43,7 +44,7 @@ def find_similar_sentences(query, target_sentences, n=5):
     return top_indices
 
 # settings
-selected_model_name = st.sidebar.selectbox('Similarity model', options=supported_models) 
+selected_model_name = supported_models.get(st.sidebar.selectbox('Similarity model', options=supported_models.keys()))
 emoji_count = st.sidebar.slider('Emoji output count', min_value=1, max_value=10, value=5, step=1)
 
 # title and headers