add application files

app.py

@@ -285,7 +285,7 @@ def averaged_glove_embeddings_gdrive(sentence, word_index_dict, embeddings, mode
 
 
 # Task III: Sort the cosine similarity
-def get_sorted_cosine_similarity(st_session_state, embeddings_metadata):
+def get_sorted_cosine_similarity(st.session_state.text_search, embeddings_metadata):
     """
     Get sorted cosine similarity between input sentence and categories
     Steps:
@@ -296,14 +296,14 @@ def get_sorted_cosine_similarity(st_session_state, embeddings_metadata):
     5. Return sorted cosine similarity
     (50 pts)
     """
-    categories = st_session_state.categories.split(" ")
+    categories = st.session_state.categories.split(" ")
     cosine_sim = {}
     if embeddings_metadata["embedding_model"] == "glove":
         word_index_dict = embeddings_metadata["word_index_dict"]
         embeddings = embeddings_metadata["embeddings"]
         model_type = embeddings_metadata["model_type"]
-        print(f'Debug: {st_session_state.text_search}')
-        input_embedding = averaged_glove_embeddings_gdrive(st_session_state.text_search,
+        print(f'Debug: {st.session_state.text_search}')
+        input_embedding = averaged_glove_embeddings_gdrive(st.session_state.text_search,
                                                             word_index_dict,
                                                             embeddings, model_type)
         
@@ -315,16 +315,16 @@ def get_sorted_cosine_similarity(st_session_state, embeddings_metadata):
 
     else:
         model_name = embeddings_metadata["model_name"]
-        if not "cat_embed_" + model_name in st_session_state:
+        if not "cat_embed_" + model_name in st.session_state:
             get_category_embeddings(embeddings_metadata)
 
-        category_embeddings = st_session_state["cat_embed_" + model_name]
+        category_embeddings = st.session_state["cat_embed_" + model_name]
 
-        print("text_search = ", st_session_state.text_search)
+        print("text_search = ", st.session_state.text_search)
         if model_name:
-            input_embedding = get_sentence_transformer_embeddings(st_session_state.text_search, model_name=model_name)
+            input_embedding = get_sentence_transformer_embeddings(st.session_state.text_search, model_name=model_name)
         else:
-            input_embedding = get_sentence_transformer_embeddings(st_session_state.text_search)
+            input_embedding = get_sentence_transformer_embeddings(st.session_state.text_search)
         for index in range(len(categories)):
             category = categories[index]
 
@@ -332,7 +332,7 @@ def get_sorted_cosine_similarity(st_session_state, embeddings_metadata):
                 category_embedding = category_embeddings[category]
             else:
                 category_embedding = get_sentence_transformer_embeddings(category, model_name=model_name)
-                st_session_state["cat_embed_" + model_name][category] = category_embedding
+                st.session_state["cat_embed_" + model_name][category] = category_embedding
 
             cosine_sim[index] = cosine_similarity(input_embedding, category_embedding)