switch from vertex to gemini api

notebooks/03-RAG_with_LlamaIndex.ipynb

@@ -1,5 +1,12 @@
 {
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/towardsai/ai-tutor-rag-system/blob/main/notebooks/03-RAG_with_LlamaIndex.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -19,55 +26,14 @@
         "id": "BeuFJKlj9jKz",
         "outputId": "6419987a-aa8c-49f8-de20-42aa9d7528c3"
       },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.4/327.4 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.4/15.4 MB\u001b[0m \u001b[31m24.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m19.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.8/130.8 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m41.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.9/141.9 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m290.4/290.4 kB\u001b[0m \u001b[31m21.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.2/49.2 kB\u001b[0m \u001b[31m212.8 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-            "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 15.0.2 which is incompatible.\u001b[0m\u001b[31m\n",
-            "\u001b[0m"
-          ]
-        }
-      ],
-      "source": [
-        "!pip install -q llama-index==0.10.49 openai==1.35.3 llama-index-llms-vertex==0.2.0 google-cloud-aiplatform==1.56.0"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 2,
-      "metadata": {
-        "id": "XuzgSNqcABpV"
-      },
       "outputs": [],
       "source": [
-        "from google.cloud import aiplatform\n",
-        "from google.colab import auth\n",
-        "\n",
-        "# Authenticate\n",
-        "auth.authenticate_user()\n",
-        "\n",
-        "# Initialize Vertex AI by setting your project id\n",
-        "PROJECT_ID = \"[your-project-id]\"\n",
-        "aiplatform.init(project=PROJECT_ID, location='us-central1')"
+        "!pip install -q llama-index==0.10.49 llama-index-llms-gemini==0.1.11 openai==1.35.3 google-generativeai==0.5.4"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 3,
+      "execution_count": 2,
       "metadata": {
         "id": "CWholrWlt2OQ"
       },
@@ -75,8 +41,11 @@
       "source": [
         "import os\n",
         "\n",
-        "# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
-        "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\""
+        "# Set your \"OPENAI_API_KEY\" environment variable\n",
+        "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\"\n",
+        "\n",
+        "# Get your GOOGLE_API_KEY from https://aistudio.google.com/app/apikey\n",
+        "os.environ[\"GOOGLE_API_KEY\"] = \"<YOUR_GOOGLE_KEY>\""
       ]
     },
     {
@@ -108,7 +77,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": 3,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -123,7 +92,7 @@
           "text": [
             "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
             "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-            "100  169k  100  169k    0     0   645k      0 --:--:-- --:--:-- --:--:--  647k\n"
+            "100  169k  100  169k    0     0  1817k      0 --:--:-- --:--:-- --:--:-- 1823k\n"
           ]
         }
       ],
@@ -142,7 +111,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 5,
+      "execution_count": 4,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -187,7 +156,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 6,
+      "execution_count": 5,
       "metadata": {
         "id": "iXrr5-tnEfm9"
       },
@@ -201,7 +170,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 7,
+      "execution_count": 6,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
@@ -236,32 +205,14 @@
       },
       "outputs": [
         {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "6e893cde79734e408bb8d0b4305bedab",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "Parsing nodes:   0%|          | 0/14 [00:00<?, ?it/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "27fd17bf0eaa49868321cf2d31a5a0a1",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "Generating embeddings:   0%|          | 0/56 [00:00<?, ?it/s]"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/Users/omar/Documents/ai_repos/ai-tutor-rag-system/env/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+            "  from .autonotebook import tqdm as notebook_tqdm\n",
+            "Parsing nodes: 100%|██████████| 14/14 [00:00<00:00, 252.38it/s]\n",
+            "Generating embeddings: 100%|██████████| 56/56 [00:01<00:00, 41.05it/s]\n"
+          ]
         }
       ],
       "source": [
@@ -290,7 +241,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 9,
+      "execution_count": 7,
       "metadata": {
         "id": "bUaNH97dEfh9"
       },
@@ -299,16 +250,16 @@
         "# Define a query engine that is responsible for retrieving related pieces of text,\n",
         "# and using a LLM to formulate the final answer.\n",
         "\n",
-        "from llama_index.llms.vertex import Vertex\n",
+        "from llama_index.llms.gemini import Gemini\n",
         "\n",
-        "llm = Vertex(model=\"gemini-1.5-flash-001\", temperature=1, max_tokens=512)\n",
+        "llm = Gemini(model=\"models/gemini-1.5-flash\", temperature=1, max_tokens=512)\n",
         "\n",
         "query_engine = index.as_query_engine(llm=llm)"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 10,
+      "execution_count": 8,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -321,7 +272,7 @@
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "LLaMA 2 comes in four different model sizes, with 7 billion, 13 billion, 34 billion, and 70 billion parameters. \n",
+            "LLaMA 2 is available in four different sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters. \n",
             "\n"
           ]
         }
@@ -335,7 +286,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 11,
+      "execution_count": 9,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -348,7 +299,7 @@
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "The context does not provide a release date for Llama 3. \n",
+            "The context does not provide information about the release date of Llama 3. \n",
             "\n"
           ]
         }
@@ -359,15 +310,6 @@
         ")\n",
         "print(response)"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "oZt_sG86RwZ3"
-      },
-      "outputs": [],
-      "source": []
     }
   ],
   "metadata": {
@@ -379,7 +321,15 @@
       "name": "python3"
     },
     "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
       "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
       "version": "3.12.3"
     },
     "widgets": {