fix: reenable CI

applications/rag/example_notebooks/rag-kaggle-ray-sql-interactive.ipynb

@@ -37,9 +37,9 @@
    "id": "c7ff518d-f4d2-481b-b408-2c2507565611",
    "metadata": {},
    "source": [
-    "## Creating the Database Connection\n",
+    "## Download the Data\n",
     "\n",
-    "Let's now set up a connection to your CloudSQL database:"
+    "Let's now import required modules:"
    ]
   },
   {
@@ -60,42 +60,7 @@
     "from datasets import load_dataset_builder, load_dataset, Dataset\n",
     "from huggingface_hub import snapshot_download\n",
     "from google.cloud.sql.connector import Connector, IPTypes\n",
-    "import sqlalchemy\n",
-    "\n",
-    "# initialize parameters\n",
-    "\n",
-    "INSTANCE_CONNECTION_NAME = os.environ[\"CLOUDSQL_INSTANCE_CONNECTION_NAME\"]\n",
-    "print(f\"Your instance connection name is: {INSTANCE_CONNECTION_NAME}\")\n",
-    "DB_NAME = \"pgvector-database\"\n",
-    "\n",
-    "db_username_file = open(\"/etc/secret-volume/username\", \"r\")\n",
-    "DB_USER = db_username_file.read()\n",
-    "db_username_file.close()\n",
-    "\n",
-    "db_password_file = open(\"/etc/secret-volume/password\", \"r\")\n",
-    "DB_PASS = db_password_file.read()\n",
-    "db_password_file.close()\n",
-    "\n",
-    "# initialize Connector object\n",
-    "connector = Connector()\n",
-    "\n",
-    "# function to return the database connection object\n",
-    "def getconn():\n",
-    "    conn = connector.connect(\n",
-    "        INSTANCE_CONNECTION_NAME,\n",
-    "        \"pg8000\",\n",
-    "        user=DB_USER,\n",
-    "        password=DB_PASS,\n",
-    "        db=DB_NAME,\n",
-    "        ip_type=IPTypes.PRIVATE\n",
-    "    )\n",
-    "    return conn\n",
-    "\n",
-    "# create connection pool with 'creator' argument to our connection object function\n",
-    "pool = sqlalchemy.create_engine(\n",
-    "    \"postgresql+pg8000://\",\n",
-    "    creator=getconn,\n",
-    ")"
+    "import sqlalchemy"
    ]
   },
   {
@@ -123,7 +88,7 @@
     "SHARED_DATASET_BASE_PATH=\"/data/netflix-shows/\"\n",
     "REVIEWS_FILE_NAME=\"netflix_titles.csv\"\n",
     "\n",
-    "BATCH_SIZE = 100\n",
+    "BATCH_SIZE = 500\n",
     "CHUNK_SIZE = 1000 # text chunk sizes which will be converted to vector embeddings\n",
     "CHUNK_OVERLAP = 10\n",
     "TABLE_NAME = 'netflix_reviews_db'  # CloudSQL table name\n",
@@ -322,6 +287,40 @@
     "from sqlalchemy.orm import scoped_session, sessionmaker, mapped_column\n",
     "from pgvector.sqlalchemy import Vector\n",
     "\n",
+    "# initialize parameters\n",
+    "\n",
+    "INSTANCE_CONNECTION_NAME = os.environ[\"CLOUDSQL_INSTANCE_CONNECTION_NAME\"]\n",
+    "print(f\"Your instance connection name is: {INSTANCE_CONNECTION_NAME}\")\n",
+    "DB_NAME = \"pgvector-database\"\n",
+    "\n",
+    "db_username_file = open(\"/etc/secret-volume/username\", \"r\")\n",
+    "DB_USER = db_username_file.read()\n",
+    "db_username_file.close()\n",
+    "\n",
+    "db_password_file = open(\"/etc/secret-volume/password\", \"r\")\n",
+    "DB_PASS = db_password_file.read()\n",
+    "db_password_file.close()\n",
+    "\n",
+    "# initialize Connector object\n",
+    "connector = Connector()\n",
+    "\n",
+    "# function to return the database connection object\n",
+    "def getconn():\n",
+    "    conn = connector.connect(\n",
+    "        INSTANCE_CONNECTION_NAME,\n",
+    "        \"pg8000\",\n",
+    "        user=DB_USER,\n",
+    "        password=DB_PASS,\n",
+    "        db=DB_NAME,\n",
+    "        ip_type=IPTypes.PRIVATE\n",
+    "    )\n",
+    "    return conn\n",
+    "\n",
+    "# create connection pool with 'creator' argument to our connection object function\n",
+    "pool = sqlalchemy.create_engine(\n",
+    "    \"postgresql+pg8000://\",\n",
+    "    creator=getconn,\n",
+    ")\n",
     "\n",
     "Base = declarative_base()\n",
     "DBSession = scoped_session(sessionmaker())\n",