banko-ai-assistant 1.0.14__py3-none-any.whl → 1.0.15__py3-none-any.whl

banko_ai/vector_search/generator.py

@@ -86,46 +86,56 @@ class EnhancedExpenseGenerator:
             "Internet Provider", "Phone Company", "Water Company"
         ]
         
-        # Use the exact categories from the original CSV
+        # Use the exact categories from the original CSV with appropriate merchants
         self._categories = {
             "Groceries": {
                 "items": ["Fresh produce", "Dairy products", "Meat and poultry", "Pantry staples", "Organic foods", "Beverages", "Snacks"],
+                "merchants": ["Whole Foods", "Local Market", "Costco", "Walmart", "Target"],
                 "amount_range": (10, 150)
             },
             "Home Improvement": {
                 "items": ["Tools", "Hardware", "Paint", "Lumber", "Electrical supplies", "Plumbing supplies", "Garden supplies"],
+                "merchants": ["Home Depot", "Lowe's", "Ace Hardware", "IKEA"],
                 "amount_range": (20, 500)
             },
             "Electronics": {
                 "items": ["Smartphone", "Laptop", "Tablet", "Headphones", "Camera", "Gaming console", "Smart home device"],
+                "merchants": ["Apple Store", "Best Buy", "Amazon", "Target", "Walmart"],
                 "amount_range": (50, 1000)
             },
             "Subscription": {
                 "items": ["Streaming service", "Software subscription", "Gym membership", "News subscription", "Cloud storage", "Music service"],
+                "merchants": ["Netflix", "Spotify", "Planet Fitness", "Electric Company", "Internet Provider"],
                 "amount_range": (10, 50)
             },
             "Shopping": {
                 "items": ["Clothing", "Shoes", "Accessories", "Home decor", "Books", "Toys", "Beauty products"],
+                "merchants": ["Amazon", "Target", "Walmart", "IKEA", "Best Buy"],
                 "amount_range": (15, 200)
             },
             "Restaurant": {
                 "items": ["Dinner", "Lunch", "Breakfast", "Takeout", "Delivery", "Catering", "Fine dining"],
+                "merchants": ["McDonald's", "Italian Bistro", "Chipotle", "Subway", "Pizza Hut", "Domino's"],
                 "amount_range": (15, 100)
             },
             "Transport": {
                 "items": ["Uber ride", "Lyft ride", "Taxi", "Bus fare", "Train ticket", "Flight", "Car rental"],
+                "merchants": ["Uber", "Lyft", "Delta Airlines"],
                 "amount_range": (5, 500)
             },
             "Fuel": {
                 "items": ["Gas fill-up", "Electric charging", "Diesel fuel", "Premium gas", "Regular gas"],
+                "merchants": ["Shell Gas Station", "Tesla Supercharger", "Exxon", "Chevron", "BP"],
                 "amount_range": (20, 100)
             },
             "Travel": {
                 "items": ["Flight", "Hotel", "Car rental", "Travel insurance", "Airport parking", "Baggage fee"],
+                "merchants": ["Delta Airlines", "Hilton Hotels"],
                 "amount_range": (100, 2000)
             },
             "Coffee": {
                 "items": ["Coffee", "Espresso", "Latte", "Cappuccino", "Pastry", "Sandwich", "Breakfast"],
+                "merchants": ["Starbucks", "Local Market", "Whole Foods", "Costco"],
                 "amount_range": (3, 25)
             }
         }
@@ -142,8 +152,8 @@ class EnhancedExpenseGenerator:
         category = random.choice(list(self.categories.keys()))
         category_data = self.categories[category]
         
-        # Select merchant from the full merchant list (matching original CSV)
-        merchant = random.choice(self.merchants)
+        # Select merchant from category-specific merchants
+        merchant = random.choice(category_data["merchants"])
         
         # Generate amount within category range
         amount = round(random.uniform(*category_data["amount_range"]), 2)
@@ -242,10 +252,12 @@ class EnhancedExpenseGenerator:
                         df = pd.DataFrame(batch)
                         df.to_sql('expenses', conn, if_exists='append', index=False, method='multi')
                         # Transaction is automatically committed when exiting the context
-                        total_inserted += len(batch)
-                        batch_num = i//batch_size + 1
-                        print(f"✅ Batch {batch_num}/{total_batches}: {len(batch)} records inserted (Total: {total_inserted})")
-                        break  # Success, exit retry loop
+                        
+                    # Only increment counter after successful transaction
+                    total_inserted += len(batch)
+                    batch_num = i//batch_size + 1
+                    print(f"✅ Batch {batch_num}/{total_batches}: {len(batch)} records inserted (Total: {total_inserted})")
+                    break  # Success, exit retry loop
                         
                 except OperationalError as e:
                     # Check if it's a CockroachDB serialization failure (SQL state 40001)

{banko_ai_assistant-1.0.14.dist-info → banko_ai_assistant-1.0.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: banko-ai-assistant
-Version: 1.0.14
+Version: 1.0.15
 Summary: AI-powered expense analysis and RAG system with CockroachDB vector search and multi-provider AI support
 Author-email: Virag Tripathi <virag.tripathi@gmail.com>
 License-Expression: MIT

{banko_ai_assistant-1.0.14.dist-info → banko_ai_assistant-1.0.15.dist-info}/RECORD

@@ -151,14 +151,14 @@ banko_ai/utils/database.py,sha256=sJYAFTApkWReEJuMbbBDiz7XfgiiEd6lPSSyF6BQDpk,77
 banko_ai/utils/migration.py,sha256=j1lYUVZyYMcMvxZUOFymoK19QTPqkDZFXD-iysVCnQo,4764
 banko_ai/vector_search/__init__.py,sha256=vYksnkUU4FA8XBNzYZIH4FoGjXCx9oIbrDeapSzrNuE,621
 banko_ai/vector_search/enrichment.py,sha256=tgAImLehkp2kL46vI5GEHsE8B5E4gT3PweXZLqqKei4,8097
-banko_ai/vector_search/generator.py,sha256=KAXp8wr7xXI9hzYRslyMhYaFHbticbWpT-a2RmJgmy4,16087
+banko_ai/vector_search/generator.py,sha256=9fIuWdp_RCO49Ua7jDOYQOyHa6QvDbXei8T-AHccxKQ,17071
 banko_ai/vector_search/search.py,sha256=I-DgxTqib_VbRKX0Ttk9QmzGcAW2hLYm0_Y9HXSaibQ,18763
 banko_ai/web/__init__.py,sha256=hjWVVxYpIZhOAN1qBf4xTd36a5AUHM03Q8BF8pykhJQ,363
 banko_ai/web/app.py,sha256=Qdd9gIccFJ5NeEYFiwKS3evFNbba6t5LNs733isloWE,32127
 banko_ai/web/auth.py,sha256=js6qIixSFHyLbETDm8GNLCPrDkCDcaQZPFOrqtZP1uw,2125
-banko_ai_assistant-1.0.14.dist-info/licenses/LICENSE,sha256=skG0LkywIClj8fgSIXiG6o9vUDJ678BKBObIyJ19OMw,1075
-banko_ai_assistant-1.0.14.dist-info/METADATA,sha256=9R77jDJBrhg4ZdOmhIA_C7Ep7IV23KhKAAuvXfN7YD4,13505
-banko_ai_assistant-1.0.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-banko_ai_assistant-1.0.14.dist-info/entry_points.txt,sha256=IxPjBjMvbpCp-ikCA43bOSbYboTGPX4HYcZlvu2_vcA,47
-banko_ai_assistant-1.0.14.dist-info/top_level.txt,sha256=xNMa9Z67UssefOQ2ubFObtqUYIfYmCIclfz0xdo5OPE,9
-banko_ai_assistant-1.0.14.dist-info/RECORD,,
+banko_ai_assistant-1.0.15.dist-info/licenses/LICENSE,sha256=skG0LkywIClj8fgSIXiG6o9vUDJ678BKBObIyJ19OMw,1075
+banko_ai_assistant-1.0.15.dist-info/METADATA,sha256=x07Gebx_90JhzCMnMMYfa_PQzqK2AZpSd_9aH5k-_Y8,13505
+banko_ai_assistant-1.0.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+banko_ai_assistant-1.0.15.dist-info/entry_points.txt,sha256=IxPjBjMvbpCp-ikCA43bOSbYboTGPX4HYcZlvu2_vcA,47
+banko_ai_assistant-1.0.15.dist-info/top_level.txt,sha256=xNMa9Z67UssefOQ2ubFObtqUYIfYmCIclfz0xdo5OPE,9
+banko_ai_assistant-1.0.15.dist-info/RECORD,,