Debug - Data format

src/api/database.py

@@ -110,16 +110,41 @@ class Database:
             with self.lock:
                 self.pool.append(conn)
 
-    async def fetch(self, query: str, *args) -> List[Dict]:
+    # async def fetch(self, query: str, *args) -> List[Dict]:
+    #     """
+    #     Execute a SELECT query and return the results as a list of dictionaries.
+
+    #     Args:
+    #         query (str): The SQL query to execute.
+    #         *args: Query parameters.
+
+    #     Returns:
+    #         List[Dict]: A list of dictionaries where keys are column names and values are column values.
+
+    #     Raises:
+    #         QueryExecutionError: If the query execution fails.
+    #     """
+    #     try:
+    #         async with self.get_connection() as conn:
+    #             cursor = conn.cursor()
+    #             cursor.execute(query, args)
+    #             rows = cursor.fetchall()
+    #             columns = [desc[0] for desc in cursor.description]
+    #             return [dict(zip(columns, row)) for row in rows]
+    #     except Pg8000DatabaseError as e:
+    #         logger.error(f"Query execution failed: {e}")
+    #         raise QueryExecutionError(f"Failed to execute query: {query}") from e
+
+    async def fetch(self, query: str, *args) -> Dict[str, List]:
         """
-        Execute a SELECT query and return the results as a list of dictionaries.
+        Execute a SELECT query and return the results as a dictionary of lists.
 
         Args:
             query (str): The SQL query to execute.
             *args: Query parameters.
 
         Returns:
-            List[Dict]: A list of dictionaries where keys are column names and values are column values.
+            Dict[str, List]: A dictionary where keys are column names and values are lists of column values.
 
         Raises:
             QueryExecutionError: If the query execution fails.
@@ -130,7 +155,14 @@ class Database:
                 cursor.execute(query, args)
                 rows = cursor.fetchall()
                 columns = [desc[0] for desc in cursor.description]
-                return [dict(zip(columns, row)) for row in rows]
+
+                # Convert the list of dictionaries into a dictionary of lists
+                data_dict = {column: [] for column in columns}
+                for row in rows:
+                    for i, value in enumerate(row):
+                        data_dict[columns[i]].append(value)
+
+                return data_dict
         except Pg8000DatabaseError as e:
             logger.error(f"Query execution failed: {e}")
             raise QueryExecutionError(f"Failed to execute query: {query}") from e

src/main.py

@@ -367,7 +367,7 @@ async def create_embedding(
         logger.info("Fetching data from the database...")
         result = await db.fetch(request.query)
 
-        logger.info(f"{result}")
+        # logger.info(f"{result}")
 
         dataset = Dataset.from_dict(result)