From 3bd07cda68c07d5a9ddc038e13ba0efc8e3cebfe Mon Sep 17 00:00:00 2001 From: Richard Liu Date: Mon, 1 Apr 2024 22:00:27 +0000 Subject: [PATCH] fix old notebook --- .../rag-kaggle-ray-sql-latest.ipynb | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/applications/rag/example_notebooks/rag-kaggle-ray-sql-latest.ipynb b/applications/rag/example_notebooks/rag-kaggle-ray-sql-latest.ipynb index 3134e3287..db5c5f430 100644 --- a/applications/rag/example_notebooks/rag-kaggle-ray-sql-latest.ipynb +++ b/applications/rag/example_notebooks/rag-kaggle-ray-sql-latest.ipynb @@ -1,5 +1,15 @@ { "cells": [ + { + "cell_type": "markdown", + "id": "afb6fda4-ffde-4831-88a5-ae41144492b2", + "metadata": {}, + "source": [ + "# RAG-on-GKE Application\n", + "\n", + "This is a Python notebook for generating the vector embeddings used by the RAG on GKE application. For full information, please checkout the GitHub documentation [here](https://github.com/GoogleCloudPlatform/ai-on-gke/blob/main/applications/rag/README.md).\n" + ] + }, { "cell_type": "code", "execution_count": null, @@ -10,7 +20,7 @@ "# Replace these with your settings\n", "# Navigate to https://www.kaggle.com/settings/account and generate an API token to be used to setup the env variable. See https://www.kaggle.com/docs/api#authentication how to create one.\n", "KAGGLE_USERNAME = \"\"\n", - "KAGGLE_KEY = \"\"\n" + "KAGGLE_KEY = \"\"" ] }, { @@ -36,8 +46,8 @@ "\n", "# Download the zip file to local storage and then extract the desired contents directly to the GKE GCS CSI mounted bucket. The bucket is mounted at the \"/persist-data\" path in the jupyter pod.\n", "!kaggle datasets download -d shivamb/netflix-shows -p ~/data --force\n", - "!mkdir /persist-data/netflix-shows -p\n", - "!unzip -o ~/data/netflix-shows.zip -d /persist-data/netflix-shows" + "!mkdir /data/netflix-shows -p\n", + "!unzip -o ~/data/netflix-shows.zip -d /data/netflix-shows" ] }, {