Update app.py

app.py

@@ -171,25 +171,21 @@ def analyze_competitors(row, co):
     logger.info(f"Analyzing competitors for query: {row['query']}")
     query = row['query']
     our_url = row['page']
-    our_score = row['relevancy_score']
     
     competitor_urls = get_serp_results(query)
     
     results = []
-    for url in competitor_urls:
-        if url != our_url:  # Skip our URL if it's in the SERP results
-            content = fetch_content(url)
-            score = calculate_relevance_score(content, query, co)
-            results.append({'url': url, 'relevancy_score': score})
-    
-    # Add our page's data
-    results.append({'url': our_url, 'relevancy_score': our_score})
+    for url in [our_url] + competitor_urls:  # Include our URL at the beginning
+        content = fetch_content(url)
+        score = calculate_relevance_score(content, query, co)
+        results.append({'url': url, 'relevancy_score': score})
     
     results_df = pd.DataFrame(results).sort_values('relevancy_score', ascending=False)
     
     logger.info(f"Competitor analysis completed. {len(results)} results obtained.")
     return results_df
 
+
 def show_competitor_analysis(row, co):
     if st.button("Check Competitors", key=f"comp_{row['page']}"):
         logger.info(f"Competitor analysis requested for page: {row['page']}")
@@ -200,8 +196,11 @@ def show_competitor_analysis(row, co):
             
             our_rank = results_df.index[results_df['url'] == row['page']].tolist()[0] + 1
             total_results = len(results_df)
+            our_score = results_df.loc[results_df['url'] == row['page'], 'relevancy_score'].values[0]
+            
             logger.info(f"Our page ranks {our_rank} out of {total_results} in terms of relevancy score.")
-            st.write(f"Our page ranks {our_rank} out of {total_results} in terms of relevancy score.")
+            st.write(f"Our page ('{row['page']}') ranks {our_rank} out of {total_results} in terms of relevancy score.")
+            st.write(f"Our relevancy score: {our_score:.4f}")
             
             if our_rank == 1:
                 st.success("Your page has the highest relevancy score!")
@@ -318,6 +317,19 @@ def fetch_gsc_data(webproperty, search_type, start_date, end_date, dimensions, d
         show_error(e)
         return pd.DataFrame()
 
+def calculate_relevance_score(page_content, query, co):
+    logger.info(f"Calculating relevance score for query: {query}")
+    try:
+        page_embedding = co.embed(texts=[page_content], model='embed-english-v3.0', input_type='search_document').embeddings[0]
+        query_embedding = co.embed(texts=[query], model='embed-english-v3.0', input_type='search_query').embeddings[0]
+        score = cosine_similarity([query_embedding], [page_embedding])[0][0]
+        logger.debug(f"Relevance score calculated: {score}")
+        return score
+    except Exception as e:
+        logger.exception(f"Error calculating relevance score: {str(e)}")
+        st.error(f"Error calculating relevance score: {str(e)}")
+        return 0
+    
 def calculate_relevancy_scores(df, model_type):
     logging.info("Calculating relevancy scores")
     with st.spinner('Calculating relevancy scores...'):