Update app.py

app.py

@@ -183,13 +183,19 @@ def fetch_gsc_data(webproperty, search_type, start_date, end_date, dimensions, d
         show_error(e)
         return pd.DataFrame()
 
-def fetch_data_loading(webproperty, search_type, start_date, end_date, dimensions, device_type=None, model_type='english'):
-    with st.spinner('Fetching data and calculating relevancy scores...'):
-        df = fetch_gsc_data(webproperty, search_type, start_date, end_date, dimensions, device_type)
-        if not df.empty:
-            df = calculate_relevancy_scores(df, model_type)
-        processed_df = process_gsc_data(df)
-        return processed_df
+def calculate_relevancy_scores(df, model_type):
+    with st.spinner('Calculating relevancy scores...'):
+        try:
+            page_contents = [fetch_content(url) for url in df['page']]
+            page_embeddings = generate_embeddings(page_contents, model_type)
+            query_embeddings = generate_embeddings(df['query'].tolist(), model_type)
+            relevancy_scores = cosine_similarity(query_embeddings, page_embeddings).diagonal()
+            df = df.assign(relevancy_score=relevancy_scores)
+        except Exception as e:
+            st.warning(f"Error calculating relevancy scores: {e}")
+            df = df.assign(relevancy_score=0)
+    return df
+
 
 # -------------
 # Utility Functions
@@ -412,13 +418,17 @@ def main():
             selected_dimensions = show_dimensions_selector(search_type)
 
             if 'report_data' not in st.session_state:
-                st.session_state.report_data = None
+            st.session_state.report_data = None
 
             if st.button("Fetch Data"):
                 with st.spinner('Fetching data...'):
-                    st.session_state.report_data = fetch_data_loading(webproperty, search_type, start_date, end_date, selected_dimensions, model_type=model_type)  # Update this line
+                st.session_state.report_data = fetch_gsc_data(webproperty, search_type, start_date, end_date, selected_dimensions)
 
             if st.session_state.report_data is not None and not st.session_state.report_data.empty:
+                st.write("Data fetched successfully. Click the button below to calculate relevancy scores.")
+            
+                if st.button("Calculate Relevancy Scores"):
+                    st.session_state.report_data = calculate_relevancy_scores(st.session_state.report_data, model_type)
                 show_paginated_dataframe(st.session_state.report_data)
                 download_csv_link(st.session_state.report_data)
             elif st.session_state.report_data is not None: