add extra columns for feedback functionality

src/reporting/snowflake_connector.py

@@ -8,8 +8,11 @@ import os
 import json
 import logging
 from typing import Dict, Any, Optional
+
+
 from src.reporting.feedback_schema import UserFeedback
 
+
 # Try to import snowflake connector
 try:
     import snowflake.connector
@@ -79,12 +82,16 @@ class SnowflakeFeedbackConnector:
             self._connection.close()
             print("✅ Disconnected from Snowflake")
     
-    def insert_feedback(self, feedback: UserFeedback) -> bool:
+    def insert_feedback(self, feedback: UserFeedback, table_name: Optional[str] = None) -> bool:
         """Insert a single feedback record into Snowflake"""
         logger.info("=" * 80)
         logger.info("🔄 SNOWFLAKE INSERT: Starting feedback insertion process")
         logger.info(f"📝 Feedback ID: {feedback.feedback_id}")
         
+        # Get table name from parameter, env var, or default
+        if table_name is None:
+            table_name = os.getenv("SNOWFLAKE_FEEDBACK_TABLE", "USER_FEEDBACK_V3")
+        
         if not self._connection:
             logger.error("❌ Not connected to Snowflake. Call connect() first.")
             raise RuntimeError("Not connected to Snowflake. Call connect() first.")
@@ -131,38 +138,53 @@ class SnowflakeFeedbackConnector:
                 logger.error(f"❌ Could not set context: {e}")
                 raise
             
-            # Prepare data
-            logger.info("🔧 DATA PREPARATION: Preparing retrieved_data...")
-            retrieved_data_raw = feedback.to_dict()['retrieved_data']
+            # Prepare data - convert to JSON strings for VARIANT columns (same approach as old retrieved_data)
+            logger.info("🔧 DATA PREPARATION: Preparing VARIANT columns...")
+            feedback_dict = feedback.to_dict()
             
-            logger.info(f"   - Retrieved data type (raw): {type(retrieved_data_raw).__name__}")
-            logger.info(f"   - Retrieved data: {repr(retrieved_data_raw)[:200]}")
+            # Prepare transcript (ARRAY) - convert to JSON string
+            transcript_raw = feedback_dict.get('transcript', [])
+            if transcript_raw:
+                # Convert to JSON string (same approach as old retrieved_data)
+                transcript_for_db = json.dumps(transcript_raw)
+                logger.info(f"   - Transcript: {len(transcript_raw)} messages, JSON length: {len(transcript_for_db)}")
+            else:
+                transcript_for_db = None
+                logger.info("   - Transcript: None")
             
-            # If retrieved_data is already a string (from UI), parse it
-            if isinstance(retrieved_data_raw, str):
-                logger.info("   - Parsing string to Python object")
-                retrieved_data = json.loads(retrieved_data_raw)
-            elif retrieved_data_raw is None:
-                retrieved_data = None
+            # Prepare retrievals (ARRAY) - convert to JSON string
+            retrievals_raw = feedback_dict.get('retrievals', [])
+            if retrievals_raw:
+                # Convert to JSON string (same approach as old retrieved_data)
+                retrievals_for_db = json.dumps(retrievals_raw)
+                logger.info(f"   - Retrievals: {len(retrievals_raw)} entries, JSON length: {len(retrievals_for_db)}")
             else:
-                # It's already a Python object (list/dict)
-                logger.info("   - Data is already a Python object")
-                retrieved_data = retrieved_data_raw
+                retrievals_for_db = None
+                logger.info("   - Retrievals: None")
             
-            logger.info(f"   - Retrieved data size: {len(str(retrieved_data)) if retrieved_data else 0} characters")
-            logger.info(f"   - Retrieved data type: {type(retrieved_data).__name__}")
+            # Prepare feedback_score_related_retrieval_docs (OBJECT) - convert to JSON string
+            feedback_score_related_raw = feedback_dict.get('feedback_score_related_retrieval_docs')
+            if feedback_score_related_raw:
+                # Convert to JSON string (same approach as old retrieved_data)
+                feedback_score_related_for_db = json.dumps(feedback_score_related_raw)
+                logger.info(f"   - Feedback score related docs: present, JSON length: {len(feedback_score_related_for_db)}")
+            else:
+                feedback_score_related_for_db = None
+                logger.info("   - Feedback score related docs: None")
             
-            # Convert to JSON string for TEXT column
-            if retrieved_data:
-                retrieved_data_for_db = json.dumps(retrieved_data)
-                logger.info(f"   - Converting to JSON string for TEXT column")
-                logger.info(f"   - JSON string length: {len(retrieved_data_for_db)}")
+            # Prepare retrieved_data (preserved old column) - convert to JSON string
+            retrieved_data_raw = feedback_dict.get('retrieved_data')
+            if retrieved_data_raw:
+                # Convert to JSON string (same approach as old retrieved_data)
+                retrieved_data_for_db = json.dumps(retrieved_data_raw)
+                logger.info(f"   - Retrieved data (preserved): present, JSON length: {len(retrieved_data_for_db)}")
             else:
-                logger.info(f"   - Retrieved data is None, using NULL")
                 retrieved_data_for_db = None
+                logger.info("   - Retrieved data (preserved): None")
             
-            # Build SQL with retrieved_data as a TEXT column parameter
-            sql = f"""INSERT INTO user_feedback (
+            # Build SQL with new column structure
+            # Columns are VARCHAR (storing JSON strings), same approach as old retrieved_data
+            sql = f"""INSERT INTO {table_name} (
                 feedback_id,
                 open_ended_feedback,
                 score,
@@ -172,23 +194,25 @@ class SnowflakeFeedbackConnector:
                 message_count,
                 has_retrievals,
                 retrieval_count,
-                user_query,
-                bot_response,
-                created_at,
-                retrieved_data
+                transcript,
+                retrievals,
+                feedback_score_related_retrieval_docs,
+                retrieved_data,
+                created_at
             ) VALUES (
                 %(feedback_id)s, %(open_ended_feedback)s, %(score)s, %(is_feedback_about_last_retrieval)s,
                 %(conversation_id)s, %(timestamp)s, %(message_count)s, %(has_retrievals)s,
-                %(retrieval_count)s, %(user_query)s, %(bot_response)s, %(created_at)s,
-                %(retrieved_data)s
+                %(retrieval_count)s, %(transcript)s, %(retrievals)s, %(feedback_score_related_retrieval_docs)s,
+                %(retrieved_data)s, %(created_at)s
             )"""
             
             logger.info("📝 SQL PREPARATION: Building INSERT statement...")
-            logger.info(f"   - Target table: user_feedback")
+            logger.info(f"   - Target table: {table_name}")
             logger.info(f"   - Database: {self.database}")
             logger.info(f"   - Schema: {self.schema}")
             
             # Prepare parameters
+            # Pass JSON strings for VARIANT columns (same approach as old retrieved_data)
             params = {
                 'feedback_id': feedback.feedback_id,
                 'open_ended_feedback': feedback.open_ended_feedback,
@@ -199,10 +223,11 @@ class SnowflakeFeedbackConnector:
                 'message_count': feedback.message_count,
                 'has_retrievals': feedback.has_retrievals,
                 'retrieval_count': feedback.retrieval_count,
-                'user_query': feedback.user_query,
-                'bot_response': feedback.bot_response,
-                'created_at': feedback.created_at,
-                'retrieved_data': retrieved_data_for_db
+                'transcript': transcript_for_db,  # JSON string
+                'retrievals': retrievals_for_db,  # JSON string
+                'feedback_score_related_retrieval_docs': feedback_score_related_for_db,  # JSON string
+                'retrieved_data': retrieved_data_for_db,  # JSON string - preserved old column
+                'created_at': feedback.created_at
             }
             
             # Execute insert
@@ -265,12 +290,16 @@ def get_snowflake_connector_from_env() -> Optional[SnowflakeFeedbackConnector]:
     )
 
 
-def save_to_snowflake(feedback: UserFeedback) -> bool:
+def save_to_snowflake(feedback: UserFeedback, table_name: Optional[str] = None) -> bool:
     """Helper function to save feedback to Snowflake"""
     logger.info("=" * 80)
     logger.info("🔵 SNOWFLAKE SAVE: Starting save process")
     logger.info(f"📝 Feedback ID: {feedback.feedback_id}")
     
+    # Get table name from parameter or env var
+    if table_name is None:
+        table_name = os.getenv("SNOWFLAKE_FEEDBACK_TABLE", "USER_FEEDBACK_V3")
+    
     connector = get_snowflake_connector_from_env()
     
     if not connector:
@@ -285,7 +314,7 @@ def save_to_snowflake(feedback: UserFeedback) -> bool:
         logger.info("✅ SNOWFLAKE SAVE: Connection established")
         
         logger.info("📥 SNOWFLAKE SAVE: Attempting to insert feedback...")
-        success = connector.insert_feedback(feedback)
+        success = connector.insert_feedback(feedback, table_name=table_name)
         
         logger.info("🔌 SNOWFLAKE SAVE: Disconnecting...")
         connector.disconnect()
@@ -302,4 +331,3 @@ def save_to_snowflake(feedback: UserFeedback) -> bool:
         logger.error(f"   - Error: {e}")
         logger.info("=" * 80)
         return False
-