banko-ai-assistant 1.0.8__py3-none-any.whl → 1.0.10__py3-none-any.whl

banko_ai/cli.py

@@ -73,8 +73,8 @@ def run(host, port, debug, generate_data, no_data, clear_data, background):
                     click.echo("Clearing existing data...")
                     generator.clear_expenses()
                 
-                generator.generate_and_save(generate_data)
-                click.echo(f"✅ Successfully generated {generate_data} expense records")
+                actual_count = generator.generate_and_save(generate_data)
+                click.echo(f"✅ Successfully generated {actual_count} expense records")
         except Exception as e:
             click.echo(f"❌ Error generating data: {e}")
             return
@@ -220,8 +220,8 @@ def start(host, port, generate_data, no_data, clear_data):
                     click.echo("Clearing existing data...")
                     generator.clear_expenses()
                 
-                generator.generate_and_save(generate_data)
-                click.echo(f"✅ Successfully generated {generate_data} expense records")
+                actual_count = generator.generate_and_save(generate_data)
+                click.echo(f"✅ Successfully generated {actual_count} expense records")
         except Exception as e:
             click.echo(f"❌ Error generating data: {e}")
             return

banko_ai/vector_search/generator.py

@@ -224,56 +224,123 @@ class EnhancedExpenseGenerator:
         return expenses
     
     def save_expenses_to_database(self, expenses: List[Dict[str, Any]]) -> int:
-        """Save expenses to the database."""
-        try:
-            import pandas as pd
-            with self.engine.connect() as conn:
-                # Prepare data for insertion
-                data_to_insert = []
-                for expense in expenses:
-                    data_to_insert.append({
-                        'expense_id': expense['expense_id'],
-                        'user_id': expense['user_id'],
-                        'expense_date': expense['expense_date'],
-                        'expense_amount': expense['expense_amount'],
-                        'shopping_type': expense['shopping_type'],
-                        'description': expense['description'],
-                        'merchant': expense['merchant'],
-                        'payment_method': expense['payment_method'],
-                        'recurring': expense['recurring'],
-                        'tags': expense['tags'],
-                        'embedding': expense['embedding']
-                    })
-                
-                # Insert in batches
-                batch_size = 100
-                total_inserted = 0
-                
-                for i in range(0, len(data_to_insert), batch_size):
-                    batch = data_to_insert[i:i + batch_size]
-                    
-                    # Use pandas to insert the batch
-                    df = pd.DataFrame(batch)
-                    df.to_sql('expenses', conn, if_exists='append', index=False, method='multi')
-                    total_inserted += len(batch)
-                
-                return total_inserted
-                
-        except Exception as e:
-            print(f"Error saving expenses to database: {e}")
-            return 0
+        """Save expenses to the database with retry logic for CockroachDB."""
+        import pandas as pd
+        import time
+        import random
+        from sqlalchemy.exc import OperationalError
+        
+        # Prepare data for insertion
+        data_to_insert = []
+        for expense in expenses:
+            data_to_insert.append({
+                'expense_id': expense['expense_id'],
+                'user_id': expense['user_id'],
+                'expense_date': expense['expense_date'],
+                'expense_amount': expense['expense_amount'],
+                'shopping_type': expense['shopping_type'],
+                'description': expense['description'],
+                'merchant': expense['merchant'],
+                'payment_method': expense['payment_method'],
+                'recurring': expense['recurring'],
+                'tags': expense['tags'],
+                'embedding': expense['embedding']
+            })
+        
+        # Insert in smaller batches to reduce transaction conflicts
+        batch_size = 50  # Reduced from 100 to minimize conflicts
+        total_inserted = 0
+        total_batches = (len(data_to_insert) + batch_size - 1) // batch_size
+        
+        print(f"📊 Inserting {len(data_to_insert)} records in {total_batches} batches of {batch_size}")
+        
+        for i in range(0, len(data_to_insert), batch_size):
+            batch = data_to_insert[i:i + batch_size]
+            
+            # Retry logic for CockroachDB transaction conflicts
+            max_retries = 5
+            retry_count = 0
+            
+            while retry_count < max_retries:
+                try:
+                    with self.engine.connect() as conn:
+                        # Use pandas to insert the batch
+                        df = pd.DataFrame(batch)
+                        df.to_sql('expenses', conn, if_exists='append', index=False, method='multi')
+                        conn.commit()
+                        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)
+                    if "40001" in str(e) or "SerializationFailure" in str(e) or "restart transaction" in str(e).lower():
+                        retry_count += 1
+                        if retry_count < max_retries:
+                            # Exponential backoff with jitter
+                            base_delay = 0.1 * (2 ** retry_count)
+                            jitter = random.uniform(0, 0.1)
+                            delay = base_delay + jitter
+                            print(f"Transaction conflict detected, retrying in {delay:.2f}s (attempt {retry_count}/{max_retries})")
+                            time.sleep(delay)
+                            continue
+                        else:
+                            print(f"Max retries exceeded for batch {i//batch_size + 1}: {e}")
+                            return total_inserted
+                    else:
+                        # Non-retryable error
+                        print(f"Non-retryable database error: {e}")
+                        return total_inserted
+                        
+                except Exception as e:
+                    print(f"Unexpected error saving batch {i//batch_size + 1}: {e}")
+                    return total_inserted
+        
+        return total_inserted
     
     def clear_expenses(self) -> bool:
-        """Clear all expenses from the database."""
-        try:
-            from sqlalchemy import text
-            with self.engine.connect() as conn:
-                conn.execute(text("DELETE FROM expenses"))
-                conn.commit()
-                return True
-        except Exception as e:
-            print(f"Error clearing expenses: {e}")
-            return False
+        """Clear all expenses from the database with retry logic."""
+        import time
+        import random
+        from sqlalchemy import text
+        from sqlalchemy.exc import OperationalError
+        
+        max_retries = 5
+        retry_count = 0
+        
+        while retry_count < max_retries:
+            try:
+                with self.engine.connect() as conn:
+                    conn.execute(text("DELETE FROM expenses"))
+                    conn.commit()
+                    return True
+                    
+            except OperationalError as e:
+                # Check if it's a CockroachDB serialization failure (SQL state 40001)
+                if "40001" in str(e) or "SerializationFailure" in str(e) or "restart transaction" in str(e).lower():
+                    retry_count += 1
+                    if retry_count < max_retries:
+                        # Exponential backoff with jitter
+                        base_delay = 0.1 * (2 ** retry_count)
+                        jitter = random.uniform(0, 0.1)
+                        delay = base_delay + jitter
+                        print(f"Transaction conflict detected while clearing, retrying in {delay:.2f}s (attempt {retry_count}/{max_retries})")
+                        time.sleep(delay)
+                        continue
+                    else:
+                        print(f"Max retries exceeded while clearing expenses: {e}")
+                        return False
+                else:
+                    # Non-retryable error
+                    print(f"Non-retryable database error while clearing: {e}")
+                    return False
+                    
+            except Exception as e:
+                print(f"Unexpected error clearing expenses: {e}")
+                return False
+        
+        return False
     
     def get_expense_count(self) -> int:
         """Get the current number of expenses in the database."""

{banko_ai_assistant-1.0.8.dist-info → banko_ai_assistant-1.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: banko-ai-assistant
-Version: 1.0.8
+Version: 1.0.10
 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-1.0.8.dist-info → banko_ai_assistant-1.0.10.dist-info}/RECORD

@@ -1,6 +1,6 @@
 banko_ai/__init__.py,sha256=G1InyKemqQxP9xx6yGZgolBmrmOLSpBXqGYY8LaFOeo,568
 banko_ai/__main__.py,sha256=vySUZt0uAzogVu6yURIlLJ1Ig5bdxT_55oiiaiZKqA8,185
-banko_ai/cli.py,sha256=LgnGaUqsbtrymOru1IJsgTW98rN3zoq6UGKkbR8ojs8,13732
+banko_ai/cli.py,sha256=SsCsikOykmTM_uId-n0ivilKXu1hKch17XXwhMHfFnU,13760
 banko_ai/ai_providers/__init__.py,sha256=JdBgw5Mji2pe9nU-aiRYUmJuZk0q8KbcMtbpMJC5Dq8,483
 banko_ai/ai_providers/aws_provider.py,sha256=-tR-8tlEeSL-Fspx05tTMFguvQylkW_pz0PI2XJEByM,13074
 banko_ai/ai_providers/base.py,sha256=zbuAgkHIfJ0YkG83LXzieJuvXBcB2-nx7NhbL-I4Pf0,4725
@@ -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=sRnFLNG9WGfq8j44T7krxHI-Lc2RSH68mt0IT0GTHBA,10203
-banko_ai/vector_search/generator.py,sha256=b2yFIZRVkeGXOvsQmrqvLG7EygQ5RS4c6EakeYCZeMM,13439
+banko_ai/vector_search/generator.py,sha256=vEM-t6FYxcbOlpPTZ3t0oZFI9-4Hkto7YsRq81peT5M,16812
 banko_ai/vector_search/search.py,sha256=k3wo3zFJH9o-kBc-vAS-bdmM3LGX2vIk3u4cRA5QPXo,16915
 banko_ai/web/__init__.py,sha256=hjWVVxYpIZhOAN1qBf4xTd36a5AUHM03Q8BF8pykhJQ,363
 banko_ai/web/app.py,sha256=9xBe6RsyEUQvpDhsRckJ4pzk5x2RZWEhVs8DiJg4zqs,27675
 banko_ai/web/auth.py,sha256=js6qIixSFHyLbETDm8GNLCPrDkCDcaQZPFOrqtZP1uw,2125
-banko_ai_assistant-1.0.8.dist-info/licenses/LICENSE,sha256=skG0LkywIClj8fgSIXiG6o9vUDJ678BKBObIyJ19OMw,1075
-banko_ai_assistant-1.0.8.dist-info/METADATA,sha256=tfnBIaATmvJ1n3yLikkhzQZObGKCECQmNqmdB38Iq7Y,13243
-banko_ai_assistant-1.0.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-banko_ai_assistant-1.0.8.dist-info/entry_points.txt,sha256=IxPjBjMvbpCp-ikCA43bOSbYboTGPX4HYcZlvu2_vcA,47
-banko_ai_assistant-1.0.8.dist-info/top_level.txt,sha256=xNMa9Z67UssefOQ2ubFObtqUYIfYmCIclfz0xdo5OPE,9
-banko_ai_assistant-1.0.8.dist-info/RECORD,,
+banko_ai_assistant-1.0.10.dist-info/licenses/LICENSE,sha256=skG0LkywIClj8fgSIXiG6o9vUDJ678BKBObIyJ19OMw,1075
+banko_ai_assistant-1.0.10.dist-info/METADATA,sha256=Ugkk7LSgJQLwWCadl80MttT6tI4pnAswJGmmmTzNnUE,13244
+banko_ai_assistant-1.0.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+banko_ai_assistant-1.0.10.dist-info/entry_points.txt,sha256=IxPjBjMvbpCp-ikCA43bOSbYboTGPX4HYcZlvu2_vcA,47
+banko_ai_assistant-1.0.10.dist-info/top_level.txt,sha256=xNMa9Z67UssefOQ2ubFObtqUYIfYmCIclfz0xdo5OPE,9
+banko_ai_assistant-1.0.10.dist-info/RECORD,,