minor change

GoogleCloudPlatform · Feb 5, 2025 · 124e5df · 124e5df
1 parent 4a00d72
commit 124e5df
Showing 1 changed file with 34 additions and 9 deletions.
diff --git a/...use-cases/retrieval-augmented-generation/rag_pipeline_terabyte_scale_with_bigframes.ipynb b/...use-cases/retrieval-augmented-generation/rag_pipeline_terabyte_scale_with_bigframes.ipynb
@@ -2,7 +2,7 @@
   "cells": [
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "id": "ur8xi4C7S06n"
       },
@@ -104,7 +104,7 @@
       "source": [
         "# Overview\n",
         "\n",
-        "This notebook demonstrates how to use BigFrames and LangChain to build a RAG (Retrieval Augmented Generation) pipeline using Vertex AI. \n",
+        "This notebook demonstrates how to use BigFrames and LangChain to build a RAG (Retrieval Augmented Generation) pipeline using Vertex AI.\n",
         "\n",
         "Specifically, we are going to build a data pipeline capable of being deployed in a production environment with scheduled execution.\n",
         "\n",
@@ -151,9 +151,35 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tFy3H3aPgx12"
-      },
-      "outputs": [],
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tFy3H3aPgx12",
+        "outputId": "77abe225-b1ae-4e07-f251-ccb136d198ef"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m15.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.3/93.3 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.5/2.5 MB\u001b[0m \u001b[31m26.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.4/84.4 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m243.2/243.2 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m27.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.9/50.9 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h  Building wheel for swifter (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "\u001b[33m  WARNING: The script dotenv is installed in '/root/.local/bin' which is not on PATH.\n",
+            "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n",
+            "\u001b[0m\u001b[33m  WARNING: The script markdownify is installed in '/root/.local/bin' which is not on PATH.\n",
+            "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n",
+            "\u001b[0m"
+          ]
+        }
+      ],
       "source": [
         "%pip install --upgrade --user --quiet google-cloud-aiplatform  \"bigframes\" langchain markdownify swifter \"langchain-google-community[featurestore]\" langchain-google-vertexai\n"
       ]
@@ -253,8 +279,8 @@
         "from google.cloud import bigquery\n",
         "import vertexai\n",
         "\n",
-        "PROJECT_ID = \"\"  # @param {type: \"string\", placeholder: \"[your-project-id]\", isTemplate: true}\n",
-        "if not PROJECT_ID or PROJECT_ID == \"[your-project-id]\":\n",
+        "PROJECT_ID = \"\"  # @param {type: \"string\", placeholder: \"your-project-id\", isTemplate: true}\n",
+        "if not PROJECT_ID or PROJECT_ID == \"your-project-id\":\n",
         "    PROJECT_ID = str(os.environ.get(\"GOOGLE_CLOUD_PROJECT\"))\n",
         "\n",
         "# GOOGLE_CLOUD_REGION must be in a US region because the source dataset is in US\n",
@@ -951,8 +977,7 @@
   ],
   "metadata": {
     "colab": {
-      "name": "rag_pipeline_terabyte_scale_with_bigframes.ipynb",
-      "toc_visible": true
+      "provenance": []
     },
     "kernelspec": {
       "display_name": "Python 3",