Update utils.py

utils.py

@@ -39,7 +39,7 @@ class EmbeddingsSearch:
 
         self.model = emb_model
         self.metadata_df = metadata_df
-        self.embeddings = self.model.encode(self.metadata_df['desc'].tolist())
+        self.embeddings = self.model.encode(self.metadata_df['final_metadata'].tolist())
 
     def __call__(self, text: str, topk: int = 5):
         q_emb = self.model.encode([text])
@@ -101,6 +101,12 @@ metadata_df2 = xls.parse('Table explanations',header=1).dropna(axis=0,how='all')
 metadata_df2.columns = ['table','nickname','metadata']
 metadata_df2.table = metadata_df2.table.apply(lambda x: x.strip())
 metadata_df = pd.merge(metadata_df, metadata_df2, how='inner')
+table_desc = pd.read_csv("table_desc.csv", lineterminator='\n')
+table_desc.columns = ['table','desc']
+metadata_df = metadata_df.drop(['desc'], axis=1)
+metadata_df = pd.merge(metadata_df, table_desc, how='inner')
+metadata_df['final_metadata'] = metadata_df.apply(lambda x: x["desc"] + "\n" + x['metadata'], axis=1)
+
 #metadata_df.loc[metadata_df.table == 'History_All_Skus_Availability', 'table'] = 'TBL_History_All_Skus_Availability'
 #metadata_df.loc[metadata_df.table == 'daily_inventory', 'table'] = 'TBL_DAILY_INVENTORY'
 #metadata_df.loc[metadata_df.table == 'HISTORY_OpenOrderShortage', 'table'] = 'TBL_HISTORY_OpenOrderShortage'