Update app.py

app.py

@@ -5,6 +5,31 @@ import os
 import pandas as pd
 import json
 
+nlp = tl_calamancy_lg.load()
+    
+def get_most_similar_tag(user_query, dataframe):
+    # Process user query and existing queries with spaCy
+    all_queries = list(dataframe['query']) + [user_query]
+    processed_queries = [nlp(query) for query in all_queries]
+
+    # Get word vectors for each query
+    vectors = [query.vector for query in processed_queries]
+
+    # Calculate cosine similarity
+    similarity_matrix = cosine_similarity(vectors, vectors)
+
+    # Extract similarity scores for the user query
+    user_similarity_scores = similarity_matrix[-1, :-1]
+
+    # Find the index of the tag with the highest similarity score
+    most_similar_index = user_similarity_scores.argmax()
+
+    # Get the most similar tag
+    most_similar_tag = dataframe['tag'].iloc[most_similar_index]
+
+    # Return the most similar tag and its similarity score
+    return most_similar_tag, user_similarity_scores[most_similar_index]
+    
 # Get the absolute path of the script directory
 cwd = os.getcwd()
 
@@ -39,18 +64,13 @@ def main():
     # StreamLit Title
     st.title("TagaCare")
     
-    nlp = tl_calamancy_lg.load()
-    
     doc1 = nlp("Pano gamutin ang sakit sa ngipin")
     
     st.success(doc1)
-    
-    for data in patterns_data:
-        st.write(data)
-    
-    for data in responses_data:
-        st.write(data)
-    
+
+    returned_tag, returned_score = get_most_similar_tag("Anong lunas sa masakit ang likod")
+
+    st.success(returned_tag + str(returned_score))
 
 if __name__ == "__main__":
     main()