Update app.py

app.py

@@ -22,16 +22,16 @@ def fetch_data_to_dataframe(query, limit=50, source="mercadolibre"):
             return df
     return pd.DataFrame()
 
-def refinar_resultados(df):
-    # Ensure 'Title' is treated as a string and handle NaN values by replacing them with an empty string
-    df['Title'] = df['Title'].astype(str).fillna('')
-    
-    # Now apply your filtering condition
+def refinar_resultados(df, exclude_word="conjunto", include_word=False):
+    df['Title'] = df['Title'].astype(str)
     df_refinado = df[~df['Title'].str.contains("kit", case=False, na=False)]
     padrao_unidades = r'\b(\d+)\s*(unidade|unidades|pacote|pacotes|caixa|caixas)\b'
-    
-    # Since 'Title' is ensured to be a string, this should not raise the TypeError
     df_refinado = df_refinado[~df_refinado['Title'].str.contains(padrao_unidades, case=False, regex=True)]
+
+    if not include_word:
+        # Exclude results containing "conjunto" if it's not part of the original query
+        df_refinado = df_refinado[~df_refinado['Title'].str.contains(exclude_word, case=False)]
+    
     return df_refinado
 
 def get_best_match(query, choices, limit=15):
@@ -77,16 +77,17 @@ def select_nearest_items(df, query):
     return reasonable_price_df.sort_values(['Distance', 'Title_Similarity'], ascending=[True, False]).head(5)
 
 def search_with_fallback(query, df, limit=15):
-    # Start with the most specific query and progressively simplify it
     query_parts = query.split()
+    include_conjunto = "conjunto" in query.lower()
+    
     for i in range(len(query_parts), 0, -1):
-        # Construct a simplified query by progressively removing the least important terms
         simplified_query = " ".join(query_parts[:i])
-        df_filtrado = filtrar_itens_similares(df, simplified_query, limit=limit)
+        df_refinado = refinar_resultados(df, include_word=include_conjunto)
+        df_filtrado = filtrar_itens_similares(df_refinado, simplified_query, limit=limit)
+        
         if not df_filtrado.empty:
-            # Return the filtered DataFrame as soon as we get any results
             return df_filtrado
-    # If no results are found for any simplification of the query, return an empty DataFrame
+
     return pd.DataFrame()
 
 def integrated_app(query, titulo, EC, PU):
@@ -96,17 +97,19 @@ def integrated_app(query, titulo, EC, PU):
     if df_combined.empty:
         return "Nenhum dado encontrado. Tente uma consulta diferente.", pd.DataFrame()
 
-    df_refined = refinar_resultados(df_combined)
+    # Pass whether "conjunto" is part of the original query
+    include_conjunto = "conjunto" in query.lower()
+    df_refined = refinar_resultados(df_combined, include_word=include_conjunto)
+    
     df_similares = search_with_fallback(query, df_refined)
 
     if df_similares.empty:
         return "Nenhum item similar encontrado.", pd.DataFrame()
 
-    df_nearest = select_nearest_items(df_similares, query)  # Ensure this function is adapted to use the query for relevance
+    df_nearest = select_nearest_items(df_similares, query)
     if df_nearest.empty:
         return "Nenhum resultado próximo encontrado.", pd.DataFrame()
 
-    # Calculate valuation factor and final valuation based on the nearest items
     fator_avaliacao = calcular_fator_avaliacao(titulo, EC, PU)
     valor_avaliacao = df_nearest['Price'].mean() * fator_avaliacao
     return f"Valor Médio do Bem: R$ {df_nearest['Price'].mean():.2f}, Fator de Avaliação: {fator_avaliacao*100:.2f}%, Valor de Avaliação: R$ {valor_avaliacao:.2f}", df_nearest