{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNPhIDuwnBNGZxkxkMnLtTw",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "4bb1e341a77d41c9aca0e6680911fb43": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_1d1faa15f5564b68b948eaffa58626b3",
              "IPY_MODEL_df22a67ae80b4673b708eea74646be61",
              "IPY_MODEL_3657dc19b6ac477b9f05bb6519271473"
            ],
            "layout": "IPY_MODEL_9045e402f0344428acc085d63df7ff03"
          }
        },
        "1d1faa15f5564b68b948eaffa58626b3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f57a9ac0d924408fbaaac795c172862e",
            "placeholder": "​",
            "style": "IPY_MODEL_4cb8ba074b254e91b8877cc87ae0d279",
            "value": "Parsing nodes: 100%"
          }
        },
        "df22a67ae80b4673b708eea74646be61": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_cbd3e1411b2c4eeb943243c9d45245c4",
            "max": 14,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_04af736f84044e37aa6599aa708a77bc",
            "value": 14
          }
        },
        "3657dc19b6ac477b9f05bb6519271473": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_8d35ab8c65ba47e1be446b98f0942ac4",
            "placeholder": "​",
            "style": "IPY_MODEL_75e40756175f463e874630f229ef4066",
            "value": " 14/14 [00:01<00:00, 10.94it/s]"
          }
        },
        "9045e402f0344428acc085d63df7ff03": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f57a9ac0d924408fbaaac795c172862e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4cb8ba074b254e91b8877cc87ae0d279": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "cbd3e1411b2c4eeb943243c9d45245c4": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "04af736f84044e37aa6599aa708a77bc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "8d35ab8c65ba47e1be446b98f0942ac4": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "75e40756175f463e874630f229ef4066": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "a0dd5f2c99b2407f9f5705587976ae76": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_8728ca516bd0474586b19e0c9b457499",
              "IPY_MODEL_aac433a9a64c48dfb18d7a01f64d3b27",
              "IPY_MODEL_4802a63f700e48fca16b5d89fbab333d"
            ],
            "layout": "IPY_MODEL_3f55aef52aee4e77864d53e3197c3cc3"
          }
        },
        "8728ca516bd0474586b19e0c9b457499": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f41df4b6ab4c4132b0d20232002f0294",
            "placeholder": "​",
            "style": "IPY_MODEL_3a621edd23354ea5924189885c97dee4",
            "value": "Generating embeddings: 100%"
          }
        },
        "aac433a9a64c48dfb18d7a01f64d3b27": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_73d34cae940e4748a7b3127351925e65",
            "max": 108,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_2dc4a6c935ac4ef38ed9030608bd4b2f",
            "value": 108
          }
        },
        "4802a63f700e48fca16b5d89fbab333d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4fcebf4a9ef54729889cc6ad4cbe5d10",
            "placeholder": "​",
            "style": "IPY_MODEL_195aa202b03a42a3a674e9da2f13d878",
            "value": " 108/108 [00:07<00:00, 10.36it/s]"
          }
        },
        "3f55aef52aee4e77864d53e3197c3cc3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f41df4b6ab4c4132b0d20232002f0294": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3a621edd23354ea5924189885c97dee4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "73d34cae940e4748a7b3127351925e65": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2dc4a6c935ac4ef38ed9030608bd4b2f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "4fcebf4a9ef54729889cc6ad4cbe5d10": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "195aa202b03a42a3a674e9da2f13d878": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/towardsai/ai-tutor-rag-system/blob/main/notebooks/10-Adding_Reranking.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Install Packages and Setup Variables"
      ],
      "metadata": {
        "id": "-zE1h0uQV7uT"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "QPJzr-I9XQ7l",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "440f5d93-1cac-4a70-e244-5e8af314464e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m38.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.4/225.4 kB\u001b[0m \u001b[31m12.8 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[31m46.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m508.6/508.6 kB\u001b[0m \u001b[31m29.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.9/79.9 MB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.7/51.7 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m51.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.1/92.1 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.7/60.7 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.1/41.1 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m49.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m57.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.9/57.9 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.6/105.6 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m698.9/698.9 kB\u001b[0m \u001b[31m42.6 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[31m42.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m80.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.5/71.5 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m9.0 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[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.8/50.8 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[32m341.4/341.4 kB\u001b[0m \u001b[31m31.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m55.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m63.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
          ]
        }
      ],
      "source": [
        "!pip install -q llama-index==0.9.21 openai==1.6.0 tiktoken==0.5.2 chromadb==0.4.21 kaleido==0.2.1 python-multipart==0.0.6 cohere==4.39"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "# Set the \"OPENAI_API_KEY\" and \"COHERE_API_KEY\" in the Python environment.\n",
        "# Will be used by OpenAI client later.\n",
        "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\"\n",
        "os.environ[\"COHERE_API_KEY\"] = \"<YOUR_COHERE_KEY>\""
      ],
      "metadata": {
        "id": "riuXwpSPcvWC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import nest_asyncio\n",
        "\n",
        "nest_asyncio.apply()"
      ],
      "metadata": {
        "id": "jIEeZzqLbz0J"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load a Model"
      ],
      "metadata": {
        "id": "Bkgi2OrYzF7q"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.llms import OpenAI\n",
        "\n",
        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
      ],
      "metadata": {
        "id": "9oGT6crooSSj"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Create a VectoreStore"
      ],
      "metadata": {
        "id": "0BwVuJXlzHVL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import chromadb\n",
        "\n",
        "# create client and a new collection\n",
        "# chromadb.EphemeralClient saves data in-memory.\n",
        "chroma_client = chromadb.PersistentClient(path=\"./mini-llama-articles\")\n",
        "chroma_collection = chroma_client.create_collection(\"mini-llama-articles\")"
      ],
      "metadata": {
        "id": "SQP87lHczHKc"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.vector_stores import ChromaVectorStore\n",
        "\n",
        "# Define a storage context object using the created vector database.\n",
        "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)"
      ],
      "metadata": {
        "id": "zAaGcYMJzHAN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load the Dataset (CSV)"
      ],
      "metadata": {
        "id": "I9JbAzFcjkpn"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Download"
      ],
      "metadata": {
        "id": "ceveDuYdWCYk"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "The dataset includes several articles from the TowardsAI blog, which provide an in-depth explanation of the LLaMA2 model. Read the dataset as a long string."
      ],
      "metadata": {
        "id": "eZwf6pv7WFmD"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-llama-articles.csv"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wl_pbPvMlv1h",
        "outputId": "f844a7a8-484b-4693-8715-42506778b1de"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-02-06 19:06:12--  https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-llama-articles.csv\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.111.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 173646 (170K) [text/plain]\n",
            "Saving to: ‘mini-llama-articles.csv’\n",
            "\n",
            "\rmini-llama-articles   0%[                    ]       0  --.-KB/s               \rmini-llama-articles 100%[===================>] 169.58K  --.-KB/s    in 0.04s   \n",
            "\n",
            "2024-02-06 19:06:12 (4.66 MB/s) - ‘mini-llama-articles.csv’ saved [173646/173646]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Read File"
      ],
      "metadata": {
        "id": "VWBLtDbUWJfA"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import csv\n",
        "\n",
        "rows = []\n",
        "\n",
        "# Load the file as a JSON\n",
        "with open(\"./mini-llama-articles.csv\", mode=\"r\", encoding=\"utf-8\") as file:\n",
        "  csv_reader = csv.reader(file)\n",
        "\n",
        "  for idx, row in enumerate( csv_reader ):\n",
        "    if idx == 0: continue; # Skip header row\n",
        "    rows.append( row )\n",
        "\n",
        "# The number of characters in the dataset.\n",
        "len( rows )"
      ],
      "metadata": {
        "id": "0Q9sxuW0g3Gd",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "473050f8-0640-4e7c-91e7-3ea3485cfb51"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "14"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Convert to Document obj"
      ],
      "metadata": {
        "id": "S17g2RYOjmf2"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index import Document\n",
        "\n",
        "# Convert the chunks to Document objects so the LlamaIndex framework can process them.\n",
        "documents = [Document(text=row[1], metadata={\"title\": row[0], \"url\": row[2], \"source_name\": row[3]}) for row in rows]"
      ],
      "metadata": {
        "id": "YizvmXPejkJE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Transforming"
      ],
      "metadata": {
        "id": "qjuLbmFuWsyl"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.text_splitter import TokenTextSplitter\n",
        "\n",
        "# Define the splitter object that split the text into segments with 512 tokens,\n",
        "# with a 128 overlap between the segments.\n",
        "text_splitter = TokenTextSplitter(\n",
        "    separator=\" \", chunk_size=512, chunk_overlap=128\n",
        ")"
      ],
      "metadata": {
        "id": "9z3t70DGWsjO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.extractors import (\n",
        "    SummaryExtractor,\n",
        "    QuestionsAnsweredExtractor,\n",
        "    KeywordExtractor,\n",
        ")\n",
        "from llama_index.embeddings import OpenAIEmbedding\n",
        "from llama_index.ingestion import IngestionPipeline\n",
        "\n",
        "# Create the pipeline to apply the transformation on each chunk,\n",
        "# and store the transformed text in the chroma vector store.\n",
        "pipeline = IngestionPipeline(\n",
        "    transformations=[\n",
        "        text_splitter,\n",
        "        QuestionsAnsweredExtractor(questions=3, llm=llm),\n",
        "        SummaryExtractor(summaries=[\"prev\", \"self\"], llm=llm),\n",
        "        KeywordExtractor(keywords=10, llm=llm),\n",
        "        OpenAIEmbedding(),\n",
        "    ],\n",
        "    vector_store=vector_store\n",
        ")\n",
        "\n",
        "# Run the transformation pipeline.\n",
        "nodes = pipeline.run(documents=documents, show_progress=True);"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 413,
          "referenced_widgets": [
            "4bb1e341a77d41c9aca0e6680911fb43",
            "1d1faa15f5564b68b948eaffa58626b3",
            "df22a67ae80b4673b708eea74646be61",
            "3657dc19b6ac477b9f05bb6519271473",
            "9045e402f0344428acc085d63df7ff03",
            "f57a9ac0d924408fbaaac795c172862e",
            "4cb8ba074b254e91b8877cc87ae0d279",
            "cbd3e1411b2c4eeb943243c9d45245c4",
            "04af736f84044e37aa6599aa708a77bc",
            "8d35ab8c65ba47e1be446b98f0942ac4",
            "75e40756175f463e874630f229ef4066",
            "a0dd5f2c99b2407f9f5705587976ae76",
            "8728ca516bd0474586b19e0c9b457499",
            "aac433a9a64c48dfb18d7a01f64d3b27",
            "4802a63f700e48fca16b5d89fbab333d",
            "3f55aef52aee4e77864d53e3197c3cc3",
            "f41df4b6ab4c4132b0d20232002f0294",
            "3a621edd23354ea5924189885c97dee4",
            "73d34cae940e4748a7b3127351925e65",
            "2dc4a6c935ac4ef38ed9030608bd4b2f",
            "4fcebf4a9ef54729889cc6ad4cbe5d10",
            "195aa202b03a42a3a674e9da2f13d878"
          ]
        },
        "id": "P9LDJ7o-Wsc-",
        "outputId": "72b67575-2d55-4145-90be-a367f128fa44"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Parsing nodes:   0%|          | 0/14 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "4bb1e341a77d41c9aca0e6680911fb43"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "464\n",
            "452\n",
            "457\n",
            "465\n",
            "448\n",
            "468\n",
            "434\n",
            "447\n",
            "455\n",
            "445\n",
            "449\n",
            "455\n",
            "431\n",
            "453\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 108/108 [00:45<00:00,  2.39it/s]\n",
            "100%|██████████| 108/108 [01:01<00:00,  1.77it/s]\n",
            "100%|██████████| 108/108 [00:48<00:00,  2.24it/s]\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating embeddings:   0%|          | 0/108 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "a0dd5f2c99b2407f9f5705587976ae76"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len( nodes )"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mPGa85hM2P3P",
        "outputId": "4586ad85-71bd-4407-a584-326941a5f474"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "108"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Compress the vector store directory to a zip file to be able to download and use later.\n",
        "!zip -r vectorstore.zip mini-llama-articles"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OeeG3jxT0taW",
        "outputId": "8a2e3c63-c346-4034-8147-f2f1f996c326"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "  adding: mini-llama-articles/ (stored 0%)\n",
            "  adding: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/ (stored 0%)\n",
            "  adding: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/data_level0.bin (deflated 100%)\n",
            "  adding: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/header.bin (deflated 61%)\n",
            "  adding: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/link_lists.bin (stored 0%)\n",
            "  adding: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/length.bin (deflated 48%)\n",
            "  adding: mini-llama-articles/chroma.sqlite3 (deflated 65%)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load Indexes"
      ],
      "metadata": {
        "id": "OWaT6rL7ksp8"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "If you have already uploaded the zip file for the vector store checkpoint, please uncomment the code in the following cell block to extract its contents. After doing so, you will be able to load the dataset from local storage."
      ],
      "metadata": {
        "id": "6fFGWiz3hoTd"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# !unzip vectorstore.zip"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XxPMJ4tq06qx",
        "outputId": "8445e40a-b3c6-44ff-dfde-37cd4c73ffa2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  vectorstore.zip\n",
            "   creating: mini-llama-articles/\n",
            "   creating: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/\n",
            "  inflating: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/data_level0.bin  \n",
            "  inflating: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/header.bin  \n",
            " extracting: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/link_lists.bin  \n",
            "  inflating: mini-llama-articles/a361e92f-9895-41b6-ba72-4ad38e9875bd/length.bin  \n",
            "  inflating: mini-llama-articles/chroma.sqlite3  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load the vector store from the local storage.\n",
        "db = chromadb.PersistentClient(path=\"./mini-llama-articles\")\n",
        "chroma_collection = db.get_or_create_collection(\"mini-llama-articles\")\n",
        "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)"
      ],
      "metadata": {
        "id": "mXi56KTXk2sp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index import VectorStoreIndex\n",
        "\n",
        "# Create the index based on the vector store.\n",
        "index = VectorStoreIndex.from_vector_store(vector_store)"
      ],
      "metadata": {
        "id": "jKXURvLtkuTS"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Query Dataset"
      ],
      "metadata": {
        "id": "8JPD8yAinVSq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.postprocessor.cohere_rerank import CohereRerank\n",
        "\n",
        "# Define the Cohere Reranking object to return only the first two highest ranking chunks.\n",
        "cohere_rerank = CohereRerank(top_n=2)"
      ],
      "metadata": {
        "id": "BsFfFpVgn01h"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Define the ServiceCotext object to tie the LLM for generating final answer,\n",
        "# and the embedding model to help with retrieving related nodes.\n",
        "# The `node_postprocessors` function will be applied to the retrieved nodes.\n",
        "query_engine = index.as_query_engine(\n",
        "    similarity_top_k=10,\n",
        "    node_postprocessors=[cohere_rerank]\n",
        ")\n",
        "\n",
        "res = query_engine.query(\"How many parameters LLaMA2 model has?\")"
      ],
      "metadata": {
        "id": "b0gue7cyctt1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "res.response"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "id": "VKK3jMprctre",
        "outputId": "3acce09e-faa2-4acd-ac8f-f62380d91567"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The LLaMA2 model has four different sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Show the retrieved nodes\n",
        "for src in res.source_nodes:\n",
        "  print(\"Node ID\\t\", src.node_id)\n",
        "  print(\"Title\\t\", src.metadata['title'])\n",
        "  print(\"Text\\t\", src.text)\n",
        "  print(\"Score\\t\", src.score)\n",
        "  print(\"-_\"*20)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nvSmOtqBoCY2",
        "outputId": "052a70df-d98d-4a87-bb7c-9e56d34db7f7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Node ID\t 467d71eb-c7c2-4713-8a02-4df1269424ca\n",
            "Title\t The Generative AI Revolution: Exploring the Current Landscape\n",
            "Text\t Models Meta AI, formerly known as Facebook Artificial Intelligence Research (FAIR), is an artificial intelligence laboratory that aims to share open-source frameworks, tools, libraries, and models for research exploration and large-scale production deployment. In 2018, they released the open-source PyText, a modeling framework focused on NLP systems. Then, in August 2022, they announced the release of BlenderBot 3, a chatbot designed to improve conversational skills and safety. In November 2022, Meta developed a large language model called Galactica, which assists scientists with tasks such as summarizing academic papers and annotating molecules and proteins. Released in February 2023, LLaMA (Large Language Model Meta AI) is a transformer-based foundational large language model by Meta that ventures into both the AI and academic spaces. The model aims to help researchers, scientists, and engineers advance their work in exploring AI applications. It will be released under a non-commercial license to prevent misuse, and access will be granted to academic researchers, individuals, and organizations affiliated with the government, civil society, academia, and industry research facilities on a selective case-by-case basis. The sharing of codes and weights allows other researchers to test new approaches in LLMs. The LLaMA models have a range of 7 billion to 65 billion parameters. LLaMA-65B can be compared to DeepMind's Chinchilla and Google's PaLM. Publicly available unlabeled data was used to train these models, and training smaller foundational models require less computing power and resources. LLaMA 65B and 33B have been trained on 1.4 trillion tokens in 20 different languages, and according to the Facebook Artificial Intelligence Research (FAIR) team, the model's performance varies across languages. The data sources used for training included CCNet (67%), GitHub, Wikipedia, ArXiv, Stack Exchange, and books. LLaMA, like other large scale language models, has issues related to biased & toxic generation and hallucination.  6. Eleuther's GPT-Neo Models Founded in July 2020 by Connor Leahy, Sid Black, and Leo Gao, EleutherAI is a non-profit AI research lab\n",
            "Score\t 0.9852714\n",
            "-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n",
            "Node ID\t d6f533e5-fef8-469c-a313-def19fd38efe\n",
            "Title\t Meta's Llama 2: Revolutionizing Open Source Language Models for Commercial Use\n",
            "Text\t I. Llama 2: Revolutionizing Commercial Use Unlike its predecessor Llama 1, which was limited to research use, Llama 2 represents a major advancement as an open-source commercial model. Businesses can now integrate Llama 2 into products to create AI-powered applications. Availability on Azure and AWS facilitates fine-tuning and adoption. However, restrictions apply to prevent exploitation. Companies with over 700 million active daily users cannot use Llama 2. Additionally, its output cannot be used to improve other language models.  II. Llama 2 Model Flavors Llama 2 is available in four different model sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters. While 7B, 13B, and 70B have already been released, the 34B model is still awaited. The pretrained variant, trained on a whopping 2 trillion tokens, boasts a context window of 4096 tokens, twice the size of its predecessor Llama 1. Meta also released a Llama 2 fine-tuned model for chat applications that was trained on over 1 million human annotations. Such extensive training comes at a cost, with the 70B model taking a staggering 1720320 GPU hours to train. The context window's length determines the amount of content the model can process at once, making Llama 2 a powerful language model in terms of scale and efficiency.  III. Safety Considerations: A Top Priority for Meta Meta's commitment to safety and alignment shines through in Llama 2's design. The model demonstrates exceptionally low AI safety violation percentages, surpassing even ChatGPT in safety benchmarks. Finding the right balance between helpfulness and safety when optimizing a model poses significant challenges. While a highly helpful model may be capable of answering any question, including sensitive ones like \"How do I build a bomb?\", it also raises concerns about potential misuse. Thus, striking the perfect equilibrium between providing useful information and ensuring safety is paramount. However, prioritizing safety to an extreme extent can lead to a model that struggles to effectively address a diverse range of questions. This limitation could hinder the model's practical applicability and user experience. Thus, achieving\n",
            "Score\t 0.90582335\n",
            "-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Evaluate"
      ],
      "metadata": {
        "id": "iMkpzH7vvb09"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.evaluation import generate_question_context_pairs\n",
        "from llama_index.llms import OpenAI\n",
        "\n",
        "# Create questions for each segment. These questions will be used to\n",
        "# assess whether the retriever can accurately identify and return the\n",
        "# corresponding segment when queried.\n",
        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
        "rag_eval_dataset = generate_question_context_pairs(\n",
        "    nodes,\n",
        "    llm=llm,\n",
        "    num_questions_per_chunk=1\n",
        ")\n",
        "\n",
        "# We can save the evaluation dataset as a json file for later use.\n",
        "rag_eval_dataset.save_json(\"./rag_eval_dataset_rerank.json\")"
      ],
      "metadata": {
        "id": "H8a3eKgKvckU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "cb004dc9-6b49-4d10-a790-1d5257318cd7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 108/108 [05:45<00:00,  3.20s/it]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "If you have uploaded the generated question JSON file, please uncomment the code in the next cell block. This will avoid the need to generate the questions manually, saving you time and effort."
      ],
      "metadata": {
        "id": "QvZBMpsXiWEw"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# from llama_index.finetuning.embeddings.common import (\n",
        "#     EmbeddingQAFinetuneDataset,\n",
        "# )\n",
        "# rag_eval_dataset = EmbeddingQAFinetuneDataset.from_json(\n",
        "#     \"./rag_eval_dataset_rerank.json\"\n",
        "# )"
      ],
      "metadata": {
        "id": "3sA1K84U254o"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "#  A simple function to show the evaluation result.\n",
        "def display_results_retriever(name, eval_results):\n",
        "    \"\"\"Display results from evaluate.\"\"\"\n",
        "\n",
        "    metric_dicts = []\n",
        "    for eval_result in eval_results:\n",
        "        metric_dict = eval_result.metric_vals_dict\n",
        "        metric_dicts.append(metric_dict)\n",
        "\n",
        "    full_df = pd.DataFrame(metric_dicts)\n",
        "\n",
        "    hit_rate = full_df[\"hit_rate\"].mean()\n",
        "    mrr = full_df[\"mrr\"].mean()\n",
        "\n",
        "    metric_df = pd.DataFrame(\n",
        "        {\"Retriever Name\": [name], \"Hit Rate\": [hit_rate], \"MRR\": [mrr]}\n",
        "    )\n",
        "\n",
        "    return metric_df"
      ],
      "metadata": {
        "id": "H7ubvcbk27vr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.evaluation import RetrieverEvaluator\n",
        "\n",
        "# We can evaluate the retievers with different top_k values.\n",
        "for i in [2, 4, 6, 8, 10]:\n",
        "    retriever = index.as_retriever(similarity_top_k=i, node_postprocessors=[cohere_rerank])\n",
        "    retriever_evaluator = RetrieverEvaluator.from_metric_names(\n",
        "        [\"mrr\", \"hit_rate\"], retriever=retriever\n",
        "    )\n",
        "    eval_results = await retriever_evaluator.aevaluate_dataset(rag_eval_dataset)\n",
        "    print(display_results_retriever(f\"Retriever top_{i}\", eval_results))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uNLxDxoc2-Ac",
        "outputId": "f42dc98d-789f-4779-c693-0603cd43e4c9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "    Retriever Name  Hit Rate      MRR\n",
            "0  Retriever top_2  0.661308  0.54716\n",
            "    Retriever Name  Hit Rate       MRR\n",
            "0  Retriever top_4  0.773848  0.580743\n",
            "    Retriever Name  Hit Rate       MRR\n",
            "0  Retriever top_6  0.826367  0.590014\n",
            "    Retriever Name  Hit Rate       MRR\n",
            "0  Retriever top_8  0.856377  0.595979\n",
            "     Retriever Name  Hit Rate       MRR\n",
            "0  Retriever top_10  0.871383  0.596152\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "It's important to keep in mind that all the results above are based on only two samples even when the retriever fetch 10 items from the vector store. So, it means that instead of passing 10 chunks of data which translates into more API usage and higher cost, we will get the same quality by passing 2 chunk of data.\n",
        "\n",
        "The bot's hit rate without Cohere Reranking using two chunks is 0.65, while we get the 0.87 hit rate using two chunks after the Cohere's post processing."
      ],
      "metadata": {
        "id": "ikMYkBATFY3l"
      }
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "-DMSFJI8F6jl"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}