Demystifying_HuggingFace,_LangChain,_and_LlamaIndex.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "afd7a03af6044de7938faf66b6952268": {
          "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_458bba1509fb4137a55065af2a85fe39",
              "IPY_MODEL_ffb91295cf174fcc8cf23f4ac3d11c14",
              "IPY_MODEL_53b9d7ebb7354fbf8ed6263b4ed7ef0e"
            ],
            "layout": "IPY_MODEL_a5b6427a52a045a9a0f53ba5046763d9"
          }
        },
        "458bba1509fb4137a55065af2a85fe39": {
          "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_dfd14a8962424171a2ed3cac960360e7",
            "placeholder": "​",
            "style": "IPY_MODEL_11e4dddaa99e4b87ac453df388db84ba",
            "value": "instruct_pipeline.py: 100%"
          }
        },
        "ffb91295cf174fcc8cf23f4ac3d11c14": {
          "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_53bd4681620a4340b28ebe2ebe46d516",
            "max": 9160,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_fde6e7ab50734b4eb299b798ecba8edb",
            "value": 9160
          }
        },
        "53b9d7ebb7354fbf8ed6263b4ed7ef0e": {
          "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_e69be26183be4076bd9a40195b939369",
            "placeholder": "​",
            "style": "IPY_MODEL_18f1d64d13984b93a2304d159e2f0aa1",
            "value": " 9.16k/9.16k [00:00&lt;00:00, 255kB/s]"
          }
        },
        "a5b6427a52a045a9a0f53ba5046763d9": {
          "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
          }
        },
        "dfd14a8962424171a2ed3cac960360e7": {
          "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
          }
        },
        "11e4dddaa99e4b87ac453df388db84ba": {
          "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": ""
          }
        },
        "53bd4681620a4340b28ebe2ebe46d516": {
          "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
          }
        },
        "fde6e7ab50734b4eb299b798ecba8edb": {
          "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": ""
          }
        },
        "e69be26183be4076bd9a40195b939369": {
          "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
          }
        },
        "18f1d64d13984b93a2304d159e2f0aa1": {
          "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": ""
          }
        },
        "0985d04f07ca442caa58f75392517bb4": {
          "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_4f7ce9d80d6b44659c51b53128ac4ea2",
              "IPY_MODEL_24bda5941ac44e648ef31ca6550b412e",
              "IPY_MODEL_ad170b65a40a4846ba7c8798bc190317"
            ],
            "layout": "IPY_MODEL_f9d8a4ee1b7e41fdb827d2d1735f8c58"
          }
        },
        "4f7ce9d80d6b44659c51b53128ac4ea2": {
          "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_3945caf9ec6a4c949e1ccc201745adb8",
            "placeholder": "​",
            "style": "IPY_MODEL_aa18c491d119433e8f29f1cc02a4f01c",
            "value": "pytorch_model.bin: 100%"
          }
        },
        "24bda5941ac44e648ef31ca6550b412e": {
          "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_1dd3b68babdc4455b745b87d6a655148",
            "max": 5684548185,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_76d7abd1424b4a98b931ae5f78a01800",
            "value": 5684548185
          }
        },
        "ad170b65a40a4846ba7c8798bc190317": {
          "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_6954120fadb04ab1944694dbf8cb80c4",
            "placeholder": "​",
            "style": "IPY_MODEL_138efaa03f174ebeacfaa668f56c839a",
            "value": " 5.68G/5.68G [01:37&lt;00:00, 61.5MB/s]"
          }
        },
        "f9d8a4ee1b7e41fdb827d2d1735f8c58": {
          "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
          }
        },
        "3945caf9ec6a4c949e1ccc201745adb8": {
          "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
          }
        },
        "aa18c491d119433e8f29f1cc02a4f01c": {
          "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": ""
          }
        },
        "1dd3b68babdc4455b745b87d6a655148": {
          "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
          }
        },
        "76d7abd1424b4a98b931ae5f78a01800": {
          "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": ""
          }
        },
        "6954120fadb04ab1944694dbf8cb80c4": {
          "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
          }
        },
        "138efaa03f174ebeacfaa668f56c839a": {
          "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/NAGADEEP92/AI-ML-DS/blob/main/Demystifying_HuggingFace%2C_LangChain%2C_and_LlamaIndex.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Hugging Face"
      ],
      "metadata": {
        "id": "xKA9SnasForJ"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qPwShkJzEnOJ",
        "outputId": "fed6fa05-aec3-48cf-eebe-306dcf14c93f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.37.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.1)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.2)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n",
            "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.2)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.9.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n",
            "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.20.3)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.2)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.9.0)\n",
            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2024.2.2)\n",
            "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.27.2)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.25.2)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.2)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.1.0+cu121)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.20.3)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.13.1)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (4.9.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.2.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.3)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2023.6.0)\n",
            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.1.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2.31.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.66.2)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2024.2.2)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n"
          ]
        }
      ],
      "source": [
        "# Installing Hugging Face libraries\n",
        "\n",
        "%pip install transformers\n",
        "%pip install huggingface_hub\n",
        "%pip install accelerate"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Hugging Face Pipeline\n",
        "> The pipeline abstraction is a wrapper around all the other available pipelines."
      ],
      "metadata": {
        "id": "tJbOp2yCF-wR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "from transformers import pipeline"
      ],
      "metadata": {
        "id": "_KSZx6nuF2nk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Example: Summarization"
      ],
      "metadata": {
        "id": "rGN3z9YlHEp9"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "summarizer = pipeline(\"summarization\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xu_RD8O9F8SH",
        "outputId": "3414e923-e3de-4285-c4f3-99bdf5f7283f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "No model was supplied, defaulted to sshleifer/distilbart-cnn-12-6 and revision a4f8f3e (https://huggingface.co/sshleifer/distilbart-cnn-12-6).\n",
            "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "wikipedia_text = \"\"\"The Fédération internationale de football association (French for 'International Association Football Federation';\n",
        "[3] abbreviated as FIFA and pronounced in English as /ˈfiːfə/) is the international governing body of association football, beach soccer,\n",
        "and futsal. It was founded in 1904[4] to oversee international competition among the national associations of Belgium, Denmark, France,\n",
        "Germany, the Netherlands, Spain, Sweden and Switzerland. Headquartered in Zürich, Switzerland, its membership now comprises 211 national\n",
        "associations. These national associations must also be members of one of the six regional confederations into which the world is divided:\n",
        "CAF (Africa), AFC (Asia and Australia), UEFA (Europe), CONCACAF (North & Central America and the Caribbean), OFC (Oceania) and CONMEBOL\n",
        "(South America). It is most notable for the FIFA World Cup, held every four years.\n",
        "FIFA outlines several objectives in its organizational statutes, including growing association football internationally, providing efforts\n",
        "to ensure it is accessible to everyone, and advocating for integrity and fair play.[5] It is responsible for the organization and promotion\n",
        "of association football's major international tournaments, notably the World Cup which commenced in 1930, and the Women's World Cup which\n",
        "began in 1991. Although FIFA does not solely set the laws of the game, that being the responsibility of the International Football Association\n",
        "Board of which FIFA is a member, it applies and enforces the rules across all FIFA competitions.[6] All FIFA tournaments generate revenue from\n",
        "sponsorships; in 2022, FIFA had revenues of over US $5.8 billion, ending the 2019–2022 cycle with a net positive of US$1.2 billion, and cash\n",
        "reserves of over US$3.9 billion.[7]\n",
        "Reports by investigative journalists have linked FIFA leadership with corruption, bribery, and vote-rigging related to the election of FIFA\n",
        "president Sepp Blatter and the organization's decision to award the 2018 and 2022 World Cups to Russia and Qatar, respectively. These\n",
        "allegations led to the indictments of nine high-ranking FIFA officials and five corporate executives by the U.S. Department of Justice\n",
        "on charges including racketeering, wire fraud, and money laundering. On 27 May 2015, several of these officials were arrested by Swiss\n",
        "authorities, who launched a simultaneous but separate criminal investigation into how the organization awarded the 2018 and 2022 World Cups.\n",
        "Those among these officials who were also indicted in the U.S. are expected to be extradited to face charges there as well.[8][9][10]\n",
        "Many officials were suspended by FIFA's ethics committee including Sepp Blatter[11] and Michel Platini.[12] In early 2017, reports became\n",
        "public about FIFA president Gianni Infantino attempting to prevent the re-elections[13] of both chairmen of the ethics committee,\n",
        "Cornel Borbély and Hans-Joachim Eckert, during the FIFA congress in May 2017.[14][15] On 9 May 2017, following Infantino's proposal,[16]\n",
        "FIFA Council decided not to renew the mandates of Borbély and Eckert.[16] Together with the chairmen, 11 of 13 committee members were\n",
        "removed. FIFA has been suspected of corruption regarding the Qatar 2022 FIFA World Cup.[17]\n",
        "\"\"\"\n",
        "\n",
        "result = summarizer(wikipedia_text, max_length=150, min_length=30)"
      ],
      "metadata": {
        "id": "tj_N6HGZGQ1K"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "result[0]['summary_text']"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 86
        },
        "id": "NjgMfnPIGxbR",
        "outputId": "61fe0d46-9288-4d98-9551-ce0c00637a31"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' FIFA is the international governing body of association football, beach soccer, and futsal . It was founded in 1904 to oversee international competition among the national associations of Belgium, Denmark, France, Germany, the Netherlands, Spain, Sweden and Switzerland . It is most notable for the FIFA World Cup, held every four years . FIFA does not set the laws of the game but enforces the rules across all FIFA competitions .'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 114
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Example Sentiment Analysis"
      ],
      "metadata": {
        "id": "ywX4vbgtHLGL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "sentiment = pipeline('sentiment-analysis')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TpYknGnvHQc2",
        "outputId": "a899113c-291e-420d-b96e-5981200e296c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "No model was supplied, defaulted to distilbert-base-uncased-finetuned-sst-2-english and revision af0f99b (https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english).\n",
            "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "text = ['I am a big fan of FIFA', 'I did not enjoy the last soccer game', 'I would watch a soccer game over a tennis match']\n",
        "sentiment_result = sentiment(text)"
      ],
      "metadata": {
        "id": "Pjfbkf7rG6mk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "for r,t in zip(sentiment_result, text):\n",
        "  print(t, '-->', r['label'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "trcfD8bwHVws",
        "outputId": "5bb899c3-eec0-4eb4-9a53-064d23679e21"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "I am a big fan of FIFA --> POSITIVE\n",
            "I did not enjoy the last soccer game --> NEGATIVE\n",
            "I would watch a soccer game over a tennis match --> NEGATIVE\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Example Translation"
      ],
      "metadata": {
        "id": "zZYHkaJ-HkMu"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "translator = pipeline(\"translation\", model=\"Helsinki-NLP/opus-mt-en-fr\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S1PWZLSoHgkD",
        "outputId": "6f5702a9-f391-4c84-c8b4-1a628fb514da"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/transformers/models/marian/tokenization_marian.py:197: UserWarning: Recommended: pip install sacremoses.\n",
            "  warnings.warn(\"Recommended: pip install sacremoses.\")\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# translate the previous summary\n",
        "translator(result[0]['summary_text'])\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gGV2ypV7Hm7x",
        "outputId": "e98099a2-e131-4c12-a765-0564400b58c1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[{'translation_text': 'Il a été fondé en 1904 pour superviser la compétition internationale entre les associations nationales de Belgique, Danemark, France, Allemagne, Pays-Bas, Espagne, Suède et Suisse. Il est le plus remarquable pour la Coupe du monde FIFA, tenue tous les quatre ans. FIFA ne fixe pas les lois du jeu mais fait appliquer les règles dans toutes les compétitions FIFA.'}]"
            ]
          },
          "metadata": {},
          "execution_count": 119
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pipe = pipeline(\"text-generation\", model=\"databricks/dolly-v2-3b\", trust_remote_code=True)"
      ],
      "metadata": {
        "id": "pnkg1MRRHzox",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 152,
          "referenced_widgets": [
            "afd7a03af6044de7938faf66b6952268",
            "458bba1509fb4137a55065af2a85fe39",
            "ffb91295cf174fcc8cf23f4ac3d11c14",
            "53b9d7ebb7354fbf8ed6263b4ed7ef0e",
            "a5b6427a52a045a9a0f53ba5046763d9",
            "dfd14a8962424171a2ed3cac960360e7",
            "11e4dddaa99e4b87ac453df388db84ba",
            "53bd4681620a4340b28ebe2ebe46d516",
            "fde6e7ab50734b4eb299b798ecba8edb",
            "e69be26183be4076bd9a40195b939369",
            "18f1d64d13984b93a2304d159e2f0aa1",
            "0985d04f07ca442caa58f75392517bb4",
            "4f7ce9d80d6b44659c51b53128ac4ea2",
            "24bda5941ac44e648ef31ca6550b412e",
            "ad170b65a40a4846ba7c8798bc190317",
            "f9d8a4ee1b7e41fdb827d2d1735f8c58",
            "3945caf9ec6a4c949e1ccc201745adb8",
            "aa18c491d119433e8f29f1cc02a4f01c",
            "1dd3b68babdc4455b745b87d6a655148",
            "76d7abd1424b4a98b931ae5f78a01800",
            "6954120fadb04ab1944694dbf8cb80c4",
            "138efaa03f174ebeacfaa668f56c839a"
          ]
        },
        "outputId": "2536dcd7-3fac-4db7-a7a6-ed0b3301c504"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "instruct_pipeline.py:   0%|          | 0.00/9.16k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "afd7a03af6044de7938faf66b6952268"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "A new version of the following files was downloaded from https://huggingface.co/databricks/dolly-v2-3b:\n",
            "- instruct_pipeline.py\n",
            ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "pytorch_model.bin:   0%|          | 0.00/5.68G [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "0985d04f07ca442caa58f75392517bb4"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# LangChain"
      ],
      "metadata": {
        "id": "plcvnn7CIGAf"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Example readnig a PDF"
      ],
      "metadata": {
        "id": "W_ehzHBLIIsf"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%pip install langchain langchain-experimental langchain-openai openai pypdf"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BskSFXn7IIeQ",
        "outputId": "90d9931f-2a75-4485-821f-1c036e03f48a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.1.9)\n",
            "Requirement already satisfied: langchain-experimental in /usr/local/lib/python3.10/dist-packages (0.0.52)\n",
            "Requirement already satisfied: langchain-openai in /usr/local/lib/python3.10/dist-packages (0.0.7)\n",
            "Requirement already satisfied: openai in /usr/local/lib/python3.10/dist-packages (1.12.0)\n",
            "Requirement already satisfied: pypdf in /usr/local/lib/python3.10/dist-packages (4.0.2)\n",
            "Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n",
            "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.27)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.3)\n",
            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)\n",
            "Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.6.4)\n",
            "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.33)\n",
            "Requirement already satisfied: langchain-community<0.1,>=0.0.21 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.24)\n",
            "Requirement already satisfied: langchain-core<0.2,>=0.1.26 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.27)\n",
            "Requirement already satisfied: langsmith<0.2.0,>=0.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.9)\n",
            "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.25.2)\n",
            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.6.1)\n",
            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)\n",
            "Requirement already satisfied: tiktoken<1,>=0.5.2 in /usr/local/lib/python3.10/dist-packages (from langchain-openai) (0.6.0)\n",
            "Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai) (3.7.1)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n",
            "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from openai) (0.27.0)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.0)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.2)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai) (4.9.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.4)\n",
            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.6)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.0)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (3.21.0)\n",
            "Requirement already satisfied: typing-inspect<1,>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (0.9.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.2.2)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (1.0.4)\n",
            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai) (0.14.0)\n",
            "Requirement already satisfied: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain) (2.4)\n",
            "Requirement already satisfied: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1.26->langchain) (23.2)\n",
            "Requirement already satisfied: orjson<4.0.0,>=3.9.14 in /usr/local/lib/python3.10/dist-packages (from langsmith<0.2.0,>=0.1.0->langchain) (3.9.15)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (2.16.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2.0.7)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.3)\n",
            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken<1,>=0.5.2->langchain-openai) (2023.12.25)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.document_loaders import PyPDFLoader"
      ],
      "metadata": {
        "id": "DX-ZJDB-IFzS"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pdf_path = 'https://arxiv.org/pdf/2012.12931.pdf'"
      ],
      "metadata": {
        "id": "FVfXO8VhIcKV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pdf_loader = PyPDFLoader(file_path = pdf_path)"
      ],
      "metadata": {
        "id": "upLvzTDCIftt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pdf_data = pdf_loader.load_and_split()"
      ],
      "metadata": {
        "id": "9nKG8EZO4j9V"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "len(pdf_data)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Qs6DyNOfIgTY",
        "outputId": "95cc0750-4c0e-43c4-c770-e17be3a8e7cd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "47"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(pdf_data[0].page_content)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CZGJLvbFJQSs",
        "outputId": "62141230-1f27-4ac9-f8d3-d77c4b84209b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "On Using Classification Datasets to Evaluate Graph Outlier\n",
            "Detection: Peculiar Observations and New Insights\n",
            "LINGXIAO ZHAO, Heinz College - Information Systems & Public Policy, Carnegie Mellon University, USA\n",
            "LEMAN AKOGLU, Heinz College - Information Systems & Public Policy, Carnegie Mellon University, USA\n",
            "It is common practice of the outlier mining community to repurpose classification datasets toward evaluating\n",
            "various detection models. To that end, often a binary classification dataset is used, where samples from\n",
            "one of the classes is designated as the ‘inlier’ samples, and the other class is substantially down-sampled\n",
            "to create the (ground-truth) ‘outlier’ samples. Graph-level outlier detection (GLOD) is rarely studied but\n",
            "has many potentially influential real-world applications. In this study, we identify an intriguing issue with\n",
            "repurposing graph classification datasets for GLOD . We find that ROC-AUC performance of the models\n",
            "changes significantly (“flips” from high to very low, even worse than random) depending on which class is\n",
            "down-sampled. Interestingly, ROC-AUCs on these two variants approximately sum to 1 and their performance\n",
            "gap is amplified with increasing propagations for a certain family of propagation based outlier detection\n",
            "models. We carefully study the graph embedding space produced by propagation based models and find\n",
            "two driving factors: (1) disparity between within-class densities which is amplified by propagation, and (2)\n",
            "overlapping support (mixing of embeddings) across classes. We also study other graph embedding methods and\n",
            "downstream outlier detectors, and find that the intriguing “performance flip” issue still widely exists but which\n",
            "version of the downsample achieves higher performance may vary. Thoughtful analysis over comprehensive\n",
            "results further deeper our understanding of the established issue.\n",
            "With this study, we aim to draw attention to this (to our knowledge) previously-unnoticed issue for the\n",
            "rarely studied GLOD problem, and specifically to the following questions: 1) Given the performance flip\n",
            "issue we identified, where one version of the downsample often yields worse-than-random performance, is it\n",
            "acppropriate to evaluate GLOD by average performance across all downsampled versions when repurposing\n",
            "graph classification datasets? 2) Considering onsistently observed performance flip issue across different graph\n",
            "embedding methods we studied, is it possible to design better graph embedding methods to to overcome the\n",
            "issue? We conclude the paper with our insights to these questions.\n",
            "1 INTRODUCTION\n",
            "Outlier detection is a critical task that finds numerous applications in healthcare, security, finance,\n",
            "etc. [ 1]. Simply put, the task is to identify observations that notably stand out within large collections\n",
            "of data so as to “arouse suspicions that [they were] generated by a different mechanism” [ 12]. One\n",
            "of the key challenges of outlier detection is that it poses an unsupervised learning problem. Due\n",
            "to the rare nature of outlier instances, combined with the laborious manual (i.e., human) labeling,\n",
            "access to benchmark datasets with sufficiently many labeled ground-truth outliers is limited.\n",
            "Motivation. Lack of labeled benchmark datasets for outlier detection is not only a challenge\n",
            "for learning, but also for the evaluation of outlier models. Even if one designs unsupervised models\n",
            "for the detection task, ground-truth labels that truly reflect the nature of outliers in a domain is\n",
            "essential for the reliable error estimation of various models. Thereby, the scarcity of representative\n",
            "Authors’ addresses: Lingxiao Zhao, lingxia1@andrew.cmu.edu, Heinz College - Information Systems & Public Policy,\n",
            "Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA, 15213; Leman Akoglu, lakoglu@andrew.cmu.edu, Heinz\n",
            "College - Information Systems & Public Policy, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA, 15213.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(pdf_data[0].page_content)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y4aaTFRrJa0-",
        "outputId": "868c7951-c3c7-47ff-abf0-2476e458ed9a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "3931"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**CharacterTextSplitter**:\n",
        "* Tries to preserve paragraphs, sentences, and words as coherent units.\n",
        "* Can specify chunk_size, chunk_overlap, and separator.\n",
        "* Does not automatically handle very large chunks; instead, it relies on the user setting appropriate values for chunk_size and chunk_overlap.\n",
        "\n",
        "**RecursiveCharacterTextSplitter**:\n",
        "* Similar to CharacterTextSplitter, but adds recursive splitting capabilities.\n",
        "* Automatically handles very large chunks by attempting to split them according to the specified chunk_size and separator list.\n",
        "* If a chunk remains too large after the first round of splitting, it will try again with subsequent separators in the list."
      ],
      "metadata": {
        "id": "ih4ukxTNI_fx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter\n",
        "\n",
        "# split on \"\\n\\n\"\n",
        "splitterC = CharacterTextSplitter(\n",
        "    chunk_size = 1000,\n",
        "    chunk_overlap = 0\n",
        ")\n",
        "\n",
        "# split [\"\\n\\n\", \"\\n\", \" \", \"\" ]\n",
        "splitterR = RecursiveCharacterTextSplitter(\n",
        "     chunk_size = 1000,\n",
        "     chunk_overlap = 0\n",
        ")\n",
        "\n",
        "pdf_data_CS = pdf_loader.load_and_split(text_splitter=splitterC)\n",
        "pdf_data_RS = pdf_loader.load_and_split(text_splitter=splitterR)"
      ],
      "metadata": {
        "id": "yOI01fHAI_PY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "len(pdf_data_CS)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dhU32Me9J21L",
        "outputId": "465b3fbd-6c56-4d4c-c659-0817b47dfccb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "30"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(pdf_data_RS)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9PlNp5nrJ5AJ",
        "outputId": "dc7aa050-6f7f-4eb4-f91f-669955c1ee57"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "141"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(pdf_data_RS[0].page_content)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j4LkI2okJ7VH",
        "outputId": "3abf63b8-017e-421c-9b41-f276f4bc3385"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "On Using Classification Datasets to Evaluate Graph Outlier\n",
            "Detection: Peculiar Observations and New Insights\n",
            "LINGXIAO ZHAO, Heinz College - Information Systems & Public Policy, Carnegie Mellon University, USA\n",
            "LEMAN AKOGLU, Heinz College - Information Systems & Public Policy, Carnegie Mellon University, USA\n",
            "It is common practice of the outlier mining community to repurpose classification datasets toward evaluating\n",
            "various detection models. To that end, often a binary classification dataset is used, where samples from\n",
            "one of the classes is designated as the ‘inlier’ samples, and the other class is substantially down-sampled\n",
            "to create the (ground-truth) ‘outlier’ samples. Graph-level outlier detection (GLOD) is rarely studied but\n",
            "has many potentially influential real-world applications. In this study, we identify an intriguing issue with\n",
            "repurposing graph classification datasets for GLOD . We find that ROC-AUC performance of the models\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.summarize import load_summarize_chain\n",
        "from langchain.chat_models import ChatOpenAI"
      ],
      "metadata": {
        "id": "UkHFkTWmKFBy"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load OPENAI and API_KEY\n",
        "import configparser\n",
        "import os\n",
        "config = configparser.ConfigParser()\n",
        "\n",
        "file = '/content/env.cfg'\n",
        "config.read_file(open(file))\n",
        "\n",
        "os.environ['OPENAI_API_KEY'] = config['OPENAI']['api_key']"
      ],
      "metadata": {
        "id": "D7VZBYJEKOLU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-1106\")\n",
        "\n",
        "chain = load_summarize_chain(\n",
        "    llm=llm,\n",
        "    chain_type='stuff'\n",
        ")\n",
        "\n",
        "chain.run(pdf_data[3:5])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 103
        },
        "id": "Bf04FwacKJBq",
        "outputId": "ad2dd27b-9ecd-4113-9ae2-b7b8e5af1772"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The study addresses the issue of using classification datasets to evaluate graph outlier detection and highlights the \"performance flip\" phenomenon, where models achieve high detection performance on one variant of the dataset but fail on the other. The study identifies driving factors behind this issue, such as density disparity and overlapping support, and proposes concrete measures to quantify these factors. The study also provides insights for graph-level outlier detection and calls attention to important questions regarding fair evaluation and model selection. All methods and datasets used in the study are open-sourced for further investigation.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Example LangChain with pandas DataFrame\n",
        "* Data Source: SQLite Database\n",
        "* https://github.com/lerocha/chinook-database/blob/master/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite"
      ],
      "metadata": {
        "id": "U_8LrTARK2cx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import sqlite3"
      ],
      "metadata": {
        "id": "JysJd6dvKLEN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create connection to the Sqlite database\n",
        "con = sqlite3.connect(\"/content/Chinook_Sqlite.sqlite\")"
      ],
      "metadata": {
        "id": "-k_X0x8ALI8W"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "query = '''\n",
        "select\n",
        "\tc.*,\n",
        "\ti.InvoiceDate ,\n",
        "\ti.Total as Sales ,\n",
        "\til.UnitPrice ,\n",
        "\til.Quantity ,\n",
        "\tt.Name as TrackName,\n",
        "\ta.Title as AlbumTitle,\n",
        "\ta2.Name as ArtistName,\n",
        "\tg.Name as Genre,\n",
        "\tmt.Name as MediaType\n",
        "from\n",
        "\tCustomer c\n",
        "join Invoice i on\n",
        "\tc.CustomerId = i.CustomerId\n",
        "join InvoiceLine il on\n",
        "\ti.InvoiceId = il.InvoiceId\n",
        "join Track t on\n",
        "\til.TrackId = t.TrackId\n",
        "join Album a on\n",
        "\tt.AlbumId = a.AlbumId\n",
        "join Artist a2 on\n",
        "\ta.ArtistId = a2.ArtistId\n",
        "join Genre g on\n",
        "\tt.GenreId = g.GenreId\n",
        "join MediaType mt on\n",
        "\tt.MediaTypeId = mt.MediaTypeId\n",
        "'''"
      ],
      "metadata": {
        "id": "BZnIaBa8LN3O"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Read sqlite query results into a pandas DataFrame\n",
        "df = pd.read_sql_query(query, con)\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 470
        },
        "id": "OJoFyS2xLQdA",
        "outputId": "37feba6b-dda7-4249-88b9-78ca8db89a90"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   CustomerId FirstName LastName Company                  Address       City  \\\n",
              "0           2    Leonie   Köhler    None  Theodor-Heuss-Straße 34  Stuttgart   \n",
              "1           2    Leonie   Köhler    None  Theodor-Heuss-Straße 34  Stuttgart   \n",
              "2           4     Bjørn   Hansen    None         Ullevålsveien 14       Oslo   \n",
              "3           4     Bjørn   Hansen    None         Ullevålsveien 14       Oslo   \n",
              "4           4     Bjørn   Hansen    None         Ullevålsveien 14       Oslo   \n",
              "\n",
              "  State  Country PostalCode             Phone  ... SupportRepId  \\\n",
              "0  None  Germany      70174  +49 0711 2842222  ...            5   \n",
              "1  None  Germany      70174  +49 0711 2842222  ...            5   \n",
              "2  None   Norway       0171   +47 22 44 22 22  ...            4   \n",
              "3  None   Norway       0171   +47 22 44 22 22  ...            4   \n",
              "4  None   Norway       0171   +47 22 44 22 22  ...            4   \n",
              "\n",
              "           InvoiceDate  Sales UnitPrice  Quantity              TrackName  \\\n",
              "0  2009-01-01 00:00:00   1.98      0.99         1      Balls to the Wall   \n",
              "1  2009-01-01 00:00:00   1.98      0.99         1      Restless and Wild   \n",
              "2  2009-01-02 00:00:00   3.96      0.99         1  Put The Finger On You   \n",
              "3  2009-01-02 00:00:00   3.96      0.99         1       Inject The Venom   \n",
              "4  2009-01-02 00:00:00   3.96      0.99         1             Evil Walks   \n",
              "\n",
              "                              AlbumTitle ArtistName Genre  \\\n",
              "0                      Balls to the Wall     Accept  Rock   \n",
              "1                      Restless and Wild     Accept  Rock   \n",
              "2  For Those About To Rock We Salute You      AC/DC  Rock   \n",
              "3  For Those About To Rock We Salute You      AC/DC  Rock   \n",
              "4  For Those About To Rock We Salute You      AC/DC  Rock   \n",
              "\n",
              "                  MediaType  \n",
              "0  Protected AAC audio file  \n",
              "1  Protected AAC audio file  \n",
              "2           MPEG audio file  \n",
              "3           MPEG audio file  \n",
              "4           MPEG audio file  \n",
              "\n",
              "[5 rows x 22 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-50bf3eff-d25b-41eb-ad92-94cd8caaabaf\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>CustomerId</th>\n",
              "      <th>FirstName</th>\n",
              "      <th>LastName</th>\n",
              "      <th>Company</th>\n",
              "      <th>Address</th>\n",
              "      <th>City</th>\n",
              "      <th>State</th>\n",
              "      <th>Country</th>\n",
              "      <th>PostalCode</th>\n",
              "      <th>Phone</th>\n",
              "      <th>...</th>\n",
              "      <th>SupportRepId</th>\n",
              "      <th>InvoiceDate</th>\n",
              "      <th>Sales</th>\n",
              "      <th>UnitPrice</th>\n",
              "      <th>Quantity</th>\n",
              "      <th>TrackName</th>\n",
              "      <th>AlbumTitle</th>\n",
              "      <th>ArtistName</th>\n",
              "      <th>Genre</th>\n",
              "      <th>MediaType</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2</td>\n",
              "      <td>Leonie</td>\n",
              "      <td>Köhler</td>\n",
              "      <td>None</td>\n",
              "      <td>Theodor-Heuss-Straße 34</td>\n",
              "      <td>Stuttgart</td>\n",
              "      <td>None</td>\n",
              "      <td>Germany</td>\n",
              "      <td>70174</td>\n",
              "      <td>+49 0711 2842222</td>\n",
              "      <td>...</td>\n",
              "      <td>5</td>\n",
              "      <td>2009-01-01 00:00:00</td>\n",
              "      <td>1.98</td>\n",
              "      <td>0.99</td>\n",
              "      <td>1</td>\n",
              "      <td>Balls to the Wall</td>\n",
              "      <td>Balls to the Wall</td>\n",
              "      <td>Accept</td>\n",
              "      <td>Rock</td>\n",
              "      <td>Protected AAC audio file</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>Leonie</td>\n",
              "      <td>Köhler</td>\n",
              "      <td>None</td>\n",
              "      <td>Theodor-Heuss-Straße 34</td>\n",
              "      <td>Stuttgart</td>\n",
              "      <td>None</td>\n",
              "      <td>Germany</td>\n",
              "      <td>70174</td>\n",
              "      <td>+49 0711 2842222</td>\n",
              "      <td>...</td>\n",
              "      <td>5</td>\n",
              "      <td>2009-01-01 00:00:00</td>\n",
              "      <td>1.98</td>\n",
              "      <td>0.99</td>\n",
              "      <td>1</td>\n",
              "      <td>Restless and Wild</td>\n",
              "      <td>Restless and Wild</td>\n",
              "      <td>Accept</td>\n",
              "      <td>Rock</td>\n",
              "      <td>Protected AAC audio file</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>4</td>\n",
              "      <td>Bjørn</td>\n",
              "      <td>Hansen</td>\n",
              "      <td>None</td>\n",
              "      <td>Ullevålsveien 14</td>\n",
              "      <td>Oslo</td>\n",
              "      <td>None</td>\n",
              "      <td>Norway</td>\n",
              "      <td>0171</td>\n",
              "      <td>+47 22 44 22 22</td>\n",
              "      <td>...</td>\n",
              "      <td>4</td>\n",
              "      <td>2009-01-02 00:00:00</td>\n",
              "      <td>3.96</td>\n",
              "      <td>0.99</td>\n",
              "      <td>1</td>\n",
              "      <td>Put The Finger On You</td>\n",
              "      <td>For Those About To Rock We Salute You</td>\n",
              "      <td>AC/DC</td>\n",
              "      <td>Rock</td>\n",
              "      <td>MPEG audio file</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>Bjørn</td>\n",
              "      <td>Hansen</td>\n",
              "      <td>None</td>\n",
              "      <td>Ullevålsveien 14</td>\n",
              "      <td>Oslo</td>\n",
              "      <td>None</td>\n",
              "      <td>Norway</td>\n",
              "      <td>0171</td>\n",
              "      <td>+47 22 44 22 22</td>\n",
              "      <td>...</td>\n",
              "      <td>4</td>\n",
              "      <td>2009-01-02 00:00:00</td>\n",
              "      <td>3.96</td>\n",
              "      <td>0.99</td>\n",
              "      <td>1</td>\n",
              "      <td>Inject The Venom</td>\n",
              "      <td>For Those About To Rock We Salute You</td>\n",
              "      <td>AC/DC</td>\n",
              "      <td>Rock</td>\n",
              "      <td>MPEG audio file</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>Bjørn</td>\n",
              "      <td>Hansen</td>\n",
              "      <td>None</td>\n",
              "      <td>Ullevålsveien 14</td>\n",
              "      <td>Oslo</td>\n",
              "      <td>None</td>\n",
              "      <td>Norway</td>\n",
              "      <td>0171</td>\n",
              "      <td>+47 22 44 22 22</td>\n",
              "      <td>...</td>\n",
              "      <td>4</td>\n",
              "      <td>2009-01-02 00:00:00</td>\n",
              "      <td>3.96</td>\n",
              "      <td>0.99</td>\n",
              "      <td>1</td>\n",
              "      <td>Evil Walks</td>\n",
              "      <td>For Those About To Rock We Salute You</td>\n",
              "      <td>AC/DC</td>\n",
              "      <td>Rock</td>\n",
              "      <td>MPEG audio file</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 22 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-50bf3eff-d25b-41eb-ad92-94cd8caaabaf')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-50bf3eff-d25b-41eb-ad92-94cd8caaabaf button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-50bf3eff-d25b-41eb-ad92-94cd8caaabaf');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-0432c8c5-0663-4d05-a472-d89b5a794aa7\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0432c8c5-0663-4d05-a472-d89b5a794aa7')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-0432c8c5-0663-4d05-a472-d89b5a794aa7 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df"
            }
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TL4YYV7aLedr",
        "outputId": "71d3628f-5be3-4130-e730-8d8944b68a90"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 2240 entries, 0 to 2239\n",
            "Data columns (total 22 columns):\n",
            " #   Column        Non-Null Count  Dtype  \n",
            "---  ------        --------------  -----  \n",
            " 0   CustomerId    2240 non-null   int64  \n",
            " 1   FirstName     2240 non-null   object \n",
            " 2   LastName      2240 non-null   object \n",
            " 3   Company       380 non-null    object \n",
            " 4   Address       2240 non-null   object \n",
            " 5   City          2240 non-null   object \n",
            " 6   State         1140 non-null   object \n",
            " 7   Country       2240 non-null   object \n",
            " 8   PostalCode    2088 non-null   object \n",
            " 9   Phone         2202 non-null   object \n",
            " 10  Fax           456 non-null    object \n",
            " 11  Email         2240 non-null   object \n",
            " 12  SupportRepId  2240 non-null   int64  \n",
            " 13  InvoiceDate   2240 non-null   object \n",
            " 14  Sales         2240 non-null   float64\n",
            " 15  UnitPrice     2240 non-null   float64\n",
            " 16  Quantity      2240 non-null   int64  \n",
            " 17  TrackName     2240 non-null   object \n",
            " 18  AlbumTitle    2240 non-null   object \n",
            " 19  ArtistName    2240 non-null   object \n",
            " 20  Genre         2240 non-null   object \n",
            " 21  MediaType     2240 non-null   object \n",
            "dtypes: float64(2), int64(3), object(17)\n",
            "memory usage: 385.1+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents.agent_types import AgentType\n",
        "from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent"
      ],
      "metadata": {
        "id": "_Pvtoq9wLiq3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent = create_pandas_dataframe_agent(\n",
        "    ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
        "    df,\n",
        "    verbose=True,\n",
        "    agent_type=AgentType.OPENAI_FUNCTIONS,\n",
        ")"
      ],
      "metadata": {
        "id": "beFrv7d9Lo4H"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "13Yq2mDN7nkb",
        "outputId": "696a3c97-0597-4c52-97c1-4e32bb688c58"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2240, 22)"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"how many rows and columns are in the dataset?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "n1sIRhMQLqkh",
        "outputId": "8002f5fe-c4e7-44b2-c602-6dbb439ca1c0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m\n",
            "Invoking: `python_repl_ast` with `{'query': 'df.shape'}`\n",
            "\n",
            "\n",
            "\u001b[0m\u001b[36;1m\u001b[1;3m(2240, 22)\u001b[0m\u001b[32;1m\u001b[1;3mThe dataset has 2240 rows and 22 columns.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The dataset has 2240 rows and 22 columns.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"how many unique countries in the dataset?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "DI4FHdIULu5v",
        "outputId": "303e234e-d5d7-467c-9dd4-e7a8296f62ef"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m\n",
            "Invoking: `python_repl_ast` with `{'query': \"df['Country'].nunique()\"}`\n",
            "\n",
            "\n",
            "\u001b[0m\u001b[36;1m\u001b[1;3m24\u001b[0m\u001b[32;1m\u001b[1;3mThere are 24 unique countries in the dataset.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'There are 24 unique countries in the dataset.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"what are the top 5 most common track names and their artists?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 453
        },
        "id": "IYxQE_0tL1w2",
        "outputId": "8da9d37c-e68f-4c33-a81b-48068d7d1be0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m\n",
            "Invoking: `python_repl_ast` with `{'query': \"df.groupby(['TrackName', 'ArtistName']).size().reset_index(name='count').nlargest(5, 'count')\"}`\n",
            "\n",
            "\n",
            "\u001b[0m\u001b[36;1m\u001b[1;3m                    TrackName   ArtistName  count\n",
            "1671              The Trooper  Iron Maiden      5\n",
            "491                  Eruption    Van Halen      4\n",
            "660      Hallowed Be Thy Name  Iron Maiden      4\n",
            "1535      Sure Know Something         Kiss      4\n",
            "1648  The Number Of The Beast  Iron Maiden      4\u001b[0m\u001b[32;1m\u001b[1;3mThe top 5 most common track names and their artists are:\n",
            "\n",
            "1. Track Name: \"The Trooper\", Artist: \"Iron Maiden\", Count: 5\n",
            "2. Track Name: \"Eruption\", Artist: \"Van Halen\", Count: 4\n",
            "3. Track Name: \"Hallowed Be Thy Name\", Artist: \"Iron Maiden\", Count: 4\n",
            "4. Track Name: \"Sure Know Something\", Artist: \"Kiss\", Count: 4\n",
            "5. Track Name: \"The Number Of The Beast\", Artist: \"Iron Maiden\", Count: 4\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The top 5 most common track names and their artists are:\\n\\n1. Track Name: \"The Trooper\", Artist: \"Iron Maiden\", Count: 5\\n2. Track Name: \"Eruption\", Artist: \"Van Halen\", Count: 4\\n3. Track Name: \"Hallowed Be Thy Name\", Artist: \"Iron Maiden\", Count: 4\\n4. Track Name: \"Sure Know Something\", Artist: \"Kiss\", Count: 4\\n5. Track Name: \"The Number Of The Beast\", Artist: \"Iron Maiden\", Count: 4'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"what are the top 5 most popular artists?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 420
        },
        "id": "fodUzfs7L8p_",
        "outputId": "a4241ef9-e924-4933-825f-8ae74125b0c6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m\n",
            "Invoking: `python_repl_ast` with `{'query': \"df['ArtistName'].value_counts().head(5)\"}`\n",
            "\n",
            "\n",
            "\u001b[0m\u001b[36;1m\u001b[1;3mIron Maiden                140\n",
            "U2                         107\n",
            "Metallica                   91\n",
            "Led Zeppelin                87\n",
            "Os Paralamas Do Sucesso     45\n",
            "Name: ArtistName, dtype: int64\u001b[0m\u001b[32;1m\u001b[1;3mThe top 5 most popular artists are:\n",
            "\n",
            "1. Iron Maiden - 140\n",
            "2. U2 - 107\n",
            "3. Metallica - 91\n",
            "4. Led Zeppelin - 87\n",
            "5. Os Paralamas Do Sucesso - 45\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The top 5 most popular artists are:\\n\\n1. Iron Maiden - 140\\n2. U2 - 107\\n3. Metallica - 91\\n4. Led Zeppelin - 87\\n5. Os Paralamas Do Sucesso - 45'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# LLamaIndex"
      ],
      "metadata": {
        "id": "2AfmnHuaMIhv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%pip install llama-index"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "m0rP5vONMFGs",
        "outputId": "78e0bdf2-cb57-40a7-d035-d7eecbe0bfa3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting llama-index\n",
            "  Downloading llama_index-0.10.13.post1-py3-none-any.whl (5.7 kB)\n",
            "Collecting llama-index-agent-openai<0.2.0,>=0.1.4 (from llama-index)\n",
            "  Downloading llama_index_agent_openai-0.1.5-py3-none-any.whl (12 kB)\n",
            "Collecting llama-index-cli<0.2.0,>=0.1.2 (from llama-index)\n",
            "  Downloading llama_index_cli-0.1.5-py3-none-any.whl (25 kB)\n",
            "Collecting llama-index-core<0.11.0,>=0.10.13 (from llama-index)\n",
            "  Downloading llama_index_core-0.10.13-py3-none-any.whl (15.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.3/15.3 MB\u001b[0m \u001b[31m45.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting llama-index-embeddings-openai<0.2.0,>=0.1.5 (from llama-index)\n",
            "  Downloading llama_index_embeddings_openai-0.1.6-py3-none-any.whl (6.0 kB)\n",
            "Collecting llama-index-indices-managed-llama-cloud<0.2.0,>=0.1.2 (from llama-index)\n",
            "  Downloading llama_index_indices_managed_llama_cloud-0.1.3-py3-none-any.whl (6.6 kB)\n",
            "Collecting llama-index-legacy<0.10.0,>=0.9.48 (from llama-index)\n",
            "  Downloading llama_index_legacy-0.9.48-py3-none-any.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m52.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting llama-index-llms-openai<0.2.0,>=0.1.5 (from llama-index)\n",
            "  Downloading llama_index_llms_openai-0.1.6-py3-none-any.whl (9.4 kB)\n",
            "Collecting llama-index-multi-modal-llms-openai<0.2.0,>=0.1.3 (from llama-index)\n",
            "  Downloading llama_index_multi_modal_llms_openai-0.1.4-py3-none-any.whl (5.8 kB)\n",
            "Collecting llama-index-program-openai<0.2.0,>=0.1.3 (from llama-index)\n",
            "  Downloading llama_index_program_openai-0.1.4-py3-none-any.whl (4.1 kB)\n",
            "Collecting llama-index-question-gen-openai<0.2.0,>=0.1.2 (from llama-index)\n",
            "  Downloading llama_index_question_gen_openai-0.1.3-py3-none-any.whl (2.9 kB)\n",
            "Collecting llama-index-readers-file<0.2.0,>=0.1.4 (from llama-index)\n",
            "  Downloading llama_index_readers_file-0.1.6-py3-none-any.whl (34 kB)\n",
            "Collecting llama-index-readers-llama-parse<0.2.0,>=0.1.2 (from llama-index)\n",
            "  Downloading llama_index_readers_llama_parse-0.1.3-py3-none-any.whl (2.5 kB)\n",
            "Collecting llama-index-vector-stores-chroma<0.2.0,>=0.1.1 (from llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading llama_index_vector_stores_chroma-0.1.4-py3-none-any.whl (4.5 kB)\n",
            "Requirement already satisfied: PyYAML>=6.0.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (6.0.1)\n",
            "Requirement already satisfied: SQLAlchemy[asyncio]>=1.4.49 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (2.0.27)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.6 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (3.9.3)\n",
            "Requirement already satisfied: dataclasses-json in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (0.6.4)\n",
            "Collecting deprecated>=1.2.9.3 (from llama-index-core<0.11.0,>=0.10.13->llama-index)\n",
            "  Downloading Deprecated-1.2.14-py2.py3-none-any.whl (9.6 kB)\n",
            "Collecting dirtyjson<2.0.0,>=1.0.8 (from llama-index-core<0.11.0,>=0.10.13->llama-index)\n",
            "  Downloading dirtyjson-1.0.8-py3-none-any.whl (25 kB)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (2023.6.0)\n",
            "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (0.27.0)\n",
            "Collecting llamaindex-py-client<0.2.0,>=0.1.13 (from llama-index-core<0.11.0,>=0.10.13->llama-index)\n",
            "  Downloading llamaindex_py_client-0.1.13-py3-none-any.whl (107 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m108.0/108.0 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: nest-asyncio<2.0.0,>=1.5.8 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (1.6.0)\n",
            "Requirement already satisfied: networkx>=3.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (3.2.1)\n",
            "Requirement already satisfied: nltk<4.0.0,>=3.8.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (3.8.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (1.25.2)\n",
            "Requirement already satisfied: openai>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (1.12.0)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (1.5.3)\n",
            "Requirement already satisfied: pillow>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (9.4.0)\n",
            "Requirement already satisfied: requests>=2.31.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (2.31.0)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.2.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (8.2.3)\n",
            "Requirement already satisfied: tiktoken>=0.3.3 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (0.6.0)\n",
            "Requirement already satisfied: tqdm<5.0.0,>=4.66.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (4.66.2)\n",
            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (4.9.0)\n",
            "Requirement already satisfied: typing-inspect>=0.8.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core<0.11.0,>=0.10.13->llama-index) (0.9.0)\n",
            "Requirement already satisfied: beautifulsoup4<5.0.0,>=4.12.3 in /usr/local/lib/python3.10/dist-packages (from llama-index-readers-file<0.2.0,>=0.1.4->llama-index) (4.12.3)\n",
            "Collecting bs4<0.0.3,>=0.0.2 (from llama-index-readers-file<0.2.0,>=0.1.4->llama-index)\n",
            "  Downloading bs4-0.0.2-py2.py3-none-any.whl (1.2 kB)\n",
            "Collecting pymupdf<2.0.0,>=1.23.21 (from llama-index-readers-file<0.2.0,>=0.1.4->llama-index)\n",
            "  Downloading PyMuPDF-1.23.25-cp310-none-manylinux2014_x86_64.whl (4.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.4/4.4 MB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pypdf<5.0.0,>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-readers-file<0.2.0,>=0.1.4->llama-index) (4.0.2)\n",
            "Collecting llama-parse<0.4.0,>=0.3.3 (from llama-index-readers-llama-parse<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading llama_parse-0.3.4-py3-none-any.whl (5.3 kB)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.9.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core<0.11.0,>=0.10.13->llama-index) (4.0.3)\n",
            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4<5.0.0,>=4.12.3->llama-index-readers-file<0.2.0,>=0.1.4->llama-index) (2.5)\n",
            "Requirement already satisfied: wrapt<2,>=1.10 in /usr/local/lib/python3.10/dist-packages (from deprecated>=1.2.9.3->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.14.1)\n",
            "Collecting chromadb<0.5.0,>=0.4.22 (from llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading chromadb-0.4.23-py3-none-any.whl (521 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.7/521.7 kB\u001b[0m \u001b[31m41.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting onnxruntime<2.0.0,>=1.17.0 (from llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading onnxruntime-1.17.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (6.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m81.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tokenizers<0.16.0,>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (0.15.2)\n",
            "Requirement already satisfied: pydantic>=1.10 in /usr/local/lib/python3.10/dist-packages (from llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core<0.11.0,>=0.10.13->llama-index) (2.6.1)\n",
            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (3.7.1)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (2024.2.2)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.0.4)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (3.6)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.3.0)\n",
            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (0.14.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core<0.11.0,>=0.10.13->llama-index) (8.1.7)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.3.2)\n",
            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core<0.11.0,>=0.10.13->llama-index) (2023.12.25)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai>=1.1.0->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.7.0)\n",
            "Collecting PyMuPDFb==1.23.22 (from pymupdf<2.0.0,>=1.23.21->llama-index-readers-file<0.2.0,>=0.1.4->llama-index)\n",
            "  Downloading PyMuPDFb-1.23.22-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (30.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m30.6/30.6 MB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->llama-index-core<0.11.0,>=0.10.13->llama-index) (3.3.2)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->llama-index-core<0.11.0,>=0.10.13->llama-index) (2.0.7)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy[asyncio]>=1.4.49->llama-index-core<0.11.0,>=0.10.13->llama-index) (3.0.3)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect>=0.8.0->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.0.0)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json->llama-index-core<0.11.0,>=0.10.13->llama-index) (3.21.0)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->llama-index-core<0.11.0,>=0.10.13->llama-index) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->llama-index-core<0.11.0,>=0.10.13->llama-index) (2023.4)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.2.0)\n",
            "Requirement already satisfied: build>=1.0.3 in /usr/local/lib/python3.10/dist-packages (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.0.3)\n",
            "Collecting chroma-hnswlib==0.7.3 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading chroma_hnswlib-0.7.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m74.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting fastapi>=0.95.2 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading fastapi-0.110.0-py3-none-any.whl (92 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.1/92.1 kB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting uvicorn[standard]>=0.18.3 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading uvicorn-0.27.1-py3-none-any.whl (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting posthog>=2.4.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading posthog-3.4.2-py2.py3-none-any.whl (41 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.2/41.2 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pulsar-client>=3.1.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading pulsar_client-3.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m65.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting opentelemetry-api>=1.2.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_api-1.23.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.4/58.4 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting opentelemetry-exporter-otlp-proto-grpc>=1.2.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_exporter_otlp_proto_grpc-1.23.0-py3-none-any.whl (18 kB)\n",
            "Collecting opentelemetry-instrumentation-fastapi>=0.41b0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_instrumentation_fastapi-0.44b0-py3-none-any.whl (11 kB)\n",
            "Collecting opentelemetry-sdk>=1.2.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_sdk-1.23.0-py3-none-any.whl (105 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.7/105.7 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pypika>=0.48.9 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading PyPika-0.48.9.tar.gz (67 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m7.8 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",
            "Collecting overrides>=7.3.1 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading overrides-7.7.0-py3-none-any.whl (17 kB)\n",
            "Requirement already satisfied: importlib-resources in /usr/local/lib/python3.10/dist-packages (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (6.1.1)\n",
            "Requirement already satisfied: grpcio>=1.58.0 in /usr/local/lib/python3.10/dist-packages (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.60.1)\n",
            "Collecting bcrypt>=4.0.1 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading bcrypt-4.1.2-cp39-abi3-manylinux_2_28_x86_64.whl (698 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m698.9/698.9 kB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: typer>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (0.9.0)\n",
            "Collecting kubernetes>=28.1.0 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading kubernetes-29.0.0-py2.py3-none-any.whl (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m72.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting mmh3>=4.0.1 (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading mmh3-4.1.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (67 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: orjson>=3.9.12 in /usr/local/lib/python3.10/dist-packages (from chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (3.9.15)\n",
            "Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.10/dist-packages (from marshmallow<4.0.0,>=3.18.0->dataclasses-json->llama-index-core<0.11.0,>=0.10.13->llama-index) (23.2)\n",
            "Collecting coloredlogs (from onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (23.5.26)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (3.20.3)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.12)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core<0.11.0,>=0.10.13->llama-index) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core<0.11.0,>=0.10.13->llama-index) (2.16.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->llama-index-core<0.11.0,>=0.10.13->llama-index) (1.16.0)\n",
            "Requirement already satisfied: huggingface_hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from tokenizers<0.16.0,>=0.15.1->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (0.20.3)\n",
            "Requirement already satisfied: pyproject_hooks in /usr/local/lib/python3.10/dist-packages (from build>=1.0.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.0.0)\n",
            "Requirement already satisfied: tomli>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from build>=1.0.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (2.0.1)\n",
            "Collecting starlette<0.37.0,>=0.36.3 (from fastapi>=0.95.2->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading starlette-0.36.3-py3-none-any.whl (71 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.5/71.5 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub<1.0,>=0.16.4->tokenizers<0.16.0,>=0.15.1->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (3.13.1)\n",
            "Requirement already satisfied: google-auth>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (2.27.0)\n",
            "Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.7.0)\n",
            "Requirement already satisfied: requests-oauthlib in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.3.1)\n",
            "Requirement already satisfied: oauthlib>=3.2.2 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (3.2.2)\n",
            "Collecting importlib-metadata<7.0,>=6.0 (from opentelemetry-api>=1.2.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading importlib_metadata-6.11.0-py3-none-any.whl (23 kB)\n",
            "Requirement already satisfied: googleapis-common-protos~=1.52 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.62.0)\n",
            "Collecting opentelemetry-exporter-otlp-proto-common==1.23.0 (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_exporter_otlp_proto_common-1.23.0-py3-none-any.whl (17 kB)\n",
            "Collecting opentelemetry-proto==1.23.0 (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_proto-1.23.0-py3-none-any.whl (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.8/50.8 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting opentelemetry-instrumentation-asgi==0.44b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_instrumentation_asgi-0.44b0-py3-none-any.whl (14 kB)\n",
            "Collecting opentelemetry-instrumentation==0.44b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_instrumentation-0.44b0-py3-none-any.whl (28 kB)\n",
            "Collecting opentelemetry-semantic-conventions==0.44b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_semantic_conventions-0.44b0-py3-none-any.whl (36 kB)\n",
            "Collecting opentelemetry-util-http==0.44b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading opentelemetry_util_http-0.44b0-py3-none-any.whl (6.9 kB)\n",
            "Requirement already satisfied: setuptools>=16.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation==0.44b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (67.7.2)\n",
            "Collecting asgiref~=3.0 (from opentelemetry-instrumentation-asgi==0.44b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading asgiref-3.7.2-py3-none-any.whl (24 kB)\n",
            "Collecting monotonic>=1.5 (from posthog>=2.4.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading monotonic-1.6-py2.py3-none-any.whl (8.2 kB)\n",
            "Collecting backoff>=1.10.0 (from posthog>=2.4.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading backoff-2.2.1-py3-none-any.whl (15 kB)\n",
            "Collecting httptools>=0.5.0 (from uvicorn[standard]>=0.18.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading httptools-0.6.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (341 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m28.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting python-dotenv>=0.13 (from uvicorn[standard]>=0.18.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
            "Collecting uvloop!=0.15.0,!=0.15.1,>=0.14.0 (from uvicorn[standard]>=0.18.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading uvloop-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m60.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting watchfiles>=0.13 (from uvicorn[standard]>=0.18.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading watchfiles-0.21.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m52.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting websockets>=10.4 (from uvicorn[standard]>=0.18.3->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading websockets-12.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting humanfriendly>=9.1 (from coloredlogs->onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index)\n",
            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxruntime<2.0.0,>=1.17.0->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (1.3.0)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (5.3.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (4.9)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata<7.0,>=6.0->opentelemetry-api>=1.2.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (3.17.0)\n",
            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=28.1.0->chromadb<0.5.0,>=0.4.22->llama-index-vector-stores-chroma<0.2.0,>=0.1.1->llama-index-cli<0.2.0,>=0.1.2->llama-index) (0.5.1)\n",
            "Building wheels for collected packages: pypika\n",
            "  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pypika: filename=PyPika-0.48.9-py2.py3-none-any.whl size=53723 sha256=793c8d2c76ca585247785c6b2730560baf1d13b056cdeed64b1dce1ed21cdb2e\n",
            "  Stored in directory: /root/.cache/pip/wheels/e1/26/51/d0bffb3d2fd82256676d7ad3003faea3bd6dddc9577af665f4\n",
            "Successfully built pypika\n",
            "Installing collected packages: pypika, monotonic, mmh3, dirtyjson, websockets, uvloop, uvicorn, python-dotenv, PyMuPDFb, pulsar-client, overrides, opentelemetry-util-http, opentelemetry-semantic-conventions, opentelemetry-proto, importlib-metadata, humanfriendly, httptools, deprecated, chroma-hnswlib, bcrypt, backoff, asgiref, watchfiles, starlette, pymupdf, posthog, opentelemetry-exporter-otlp-proto-common, opentelemetry-api, coloredlogs, bs4, opentelemetry-sdk, opentelemetry-instrumentation, onnxruntime, llamaindex-py-client, kubernetes, fastapi, opentelemetry-instrumentation-asgi, opentelemetry-exporter-otlp-proto-grpc, llama-index-legacy, llama-index-core, opentelemetry-instrumentation-fastapi, llama-parse, llama-index-readers-file, llama-index-llms-openai, llama-index-indices-managed-llama-cloud, llama-index-embeddings-openai, llama-index-readers-llama-parse, llama-index-multi-modal-llms-openai, llama-index-agent-openai, chromadb, llama-index-vector-stores-chroma, llama-index-program-openai, llama-index-question-gen-openai, llama-index-cli, llama-index\n",
            "  Attempting uninstall: importlib-metadata\n",
            "    Found existing installation: importlib-metadata 7.0.1\n",
            "    Uninstalling importlib-metadata-7.0.1:\n",
            "      Successfully uninstalled importlib-metadata-7.0.1\n",
            "Successfully installed PyMuPDFb-1.23.22 asgiref-3.7.2 backoff-2.2.1 bcrypt-4.1.2 bs4-0.0.2 chroma-hnswlib-0.7.3 chromadb-0.4.23 coloredlogs-15.0.1 deprecated-1.2.14 dirtyjson-1.0.8 fastapi-0.110.0 httptools-0.6.1 humanfriendly-10.0 importlib-metadata-6.11.0 kubernetes-29.0.0 llama-index-0.10.13.post1 llama-index-agent-openai-0.1.5 llama-index-cli-0.1.5 llama-index-core-0.10.13 llama-index-embeddings-openai-0.1.6 llama-index-indices-managed-llama-cloud-0.1.3 llama-index-legacy-0.9.48 llama-index-llms-openai-0.1.6 llama-index-multi-modal-llms-openai-0.1.4 llama-index-program-openai-0.1.4 llama-index-question-gen-openai-0.1.3 llama-index-readers-file-0.1.6 llama-index-readers-llama-parse-0.1.3 llama-index-vector-stores-chroma-0.1.4 llama-parse-0.3.4 llamaindex-py-client-0.1.13 mmh3-4.1.0 monotonic-1.6 onnxruntime-1.17.1 opentelemetry-api-1.23.0 opentelemetry-exporter-otlp-proto-common-1.23.0 opentelemetry-exporter-otlp-proto-grpc-1.23.0 opentelemetry-instrumentation-0.44b0 opentelemetry-instrumentation-asgi-0.44b0 opentelemetry-instrumentation-fastapi-0.44b0 opentelemetry-proto-1.23.0 opentelemetry-sdk-1.23.0 opentelemetry-semantic-conventions-0.44b0 opentelemetry-util-http-0.44b0 overrides-7.7.0 posthog-3.4.2 pulsar-client-3.4.0 pymupdf-1.23.25 pypika-0.48.9 python-dotenv-1.0.1 starlette-0.36.3 uvicorn-0.27.1 uvloop-0.19.0 watchfiles-0.21.0 websockets-12.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Example LLamaIndex and pandas DataFrame"
      ],
      "metadata": {
        "id": "HrTZVHChM4kR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.core.query_engine import PandasQueryEngine"
      ],
      "metadata": {
        "id": "hKjHxWv-MLLp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine = PandasQueryEngine(df=df, verbose=True)"
      ],
      "metadata": {
        "id": "wgP9zF2rM3Ck"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine.query(\"what are the top 5 most popular artists?\");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CFVp0Zs7M87r",
        "outputId": "2e12263e-a398-495d-e69b-d09b6445299d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df['ArtistName'].value_counts().head(5)\n",
            "```\n",
            "> Pandas Output: Iron Maiden                140\n",
            "U2                         107\n",
            "Metallica                   91\n",
            "Led Zeppelin                87\n",
            "Os Paralamas Do Sucesso     45\n",
            "Name: ArtistName, dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df['Email'].head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IwwMNUmzND6c",
        "outputId": "c172b31f-4e1b-4703-cd9e-ead22df5dab9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    leonekohler@surfeu.de\n",
              "1    leonekohler@surfeu.de\n",
              "2    bjorn.hansen@yahoo.no\n",
              "3    bjorn.hansen@yahoo.no\n",
              "4    bjorn.hansen@yahoo.no\n",
              "Name: Email, dtype: object"
            ]
          },
          "metadata": {},
          "execution_count": 56
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine.query(\n",
        "    \"parse the emails and extract usernames\",\n",
        ");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SPdV-lonNMEI",
        "outputId": "e754dd02-c94b-40c4-dba6-940b9f56bb4a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df['Username'] = df['Email'].str.split('@').str[0]\n",
            "df['Username']\n",
            "```\n",
            "> Pandas Output: 0            leonekohler\n",
            "1            leonekohler\n",
            "2           bjorn.hansen\n",
            "3           bjorn.hansen\n",
            "4           bjorn.hansen\n",
            "              ...       \n",
            "2235    terhi.hamalainen\n",
            "2236    terhi.hamalainen\n",
            "2237    terhi.hamalainen\n",
            "2238    terhi.hamalainen\n",
            "2239        manoj.pareek\n",
            "Name: Username, Length: 2240, dtype: object\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine.query(\n",
        "    \"What is the correlation sales and unit price and quantity?\",\n",
        ");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Li2OlMlXNQUz",
        "outputId": "2b42e137-82c5-4227-c05c-c915b71ab3e5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df[['Sales', 'UnitPrice', 'Quantity']].corr()\n",
            "```\n",
            "> Pandas Output:               Sales  UnitPrice  Quantity\n",
            "Sales      1.000000   0.298778       NaN\n",
            "UnitPrice  0.298778   1.000000       NaN\n",
            "Quantity        NaN        NaN       NaN\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine.query(\n",
        "    \"show a line chart for total sales by invoice year\",\n",
        ");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 553
        },
        "id": "Sz4GTo-BNmDj",
        "outputId": "f7514667-c595-450b-fbd5-9a54b23cf3bb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df.groupby('InvoiceYear')['Sales'].sum().plot(kind='line')\n",
            "```\n",
            "> Pandas Output: Axes(0.125,0.11;0.775x0.77)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "E-Z1BxXkNxlu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Using Prompt Templates"
      ],
      "metadata": {
        "id": "TvqHNOxNObJU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "prompts = query_engine.get_prompts()\n",
        "print(prompts[\"pandas_prompt\"].template)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a1ChjSApOS78",
        "outputId": "6de57034-5ce3-407b-c67b-b26ec7050004"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "You are working with a pandas dataframe in Python.\n",
            "The name of the dataframe is `df`.\n",
            "This is the result of `print(df.head())`:\n",
            "{df_str}\n",
            "\n",
            "Follow these instructions:\n",
            "{instruction_str}\n",
            "Query: {query_str}\n",
            "\n",
            "Expression:\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(prompts[\"response_synthesis_prompt\"].template)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dh4fQHLcOai6",
        "outputId": "7d08a634-8d25-41c1-954c-f5befb247018"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Given an input question, synthesize a response from the query results.\n",
            "Query: {query_str}\n",
            "\n",
            "Pandas Instructions (optional):\n",
            "{pandas_instructions}\n",
            "\n",
            "Pandas Output: {pandas_output}\n",
            "\n",
            "Response: \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from llama_index.core import PromptTemplate\n",
        "\n",
        "new_prompt = PromptTemplate(\n",
        "    \"\"\"\\\n",
        "You are working with a pandas dataframe in Python.\n",
        "The name of the dataframe is `df`.\n",
        "This is the result of `print(df.head())`:\n",
        "{df_str}\n",
        "\n",
        "Follow these instructions:\n",
        "{instruction_str}\n",
        "Query: {query_str}\n",
        "\n",
        "Expression: \"\"\"\n",
        ")\n",
        "\n",
        "instruction_str = \"\"\"\\\n",
        "1. Convert the query to executable Python code using Pandas.\n",
        "2. The final line of code should be a Python expression that can be called with the `eval()` function.\n",
        "3. The code should represent a solution to the query.\n",
        "4. PRINT ONLY THE EXPRESSION.\n",
        "5. Do not quote the expression.\n",
        "\"\"\"\n",
        "\n",
        "query_engine.update_prompts({\"pandas_prompt\": new_prompt})"
      ],
      "metadata": {
        "id": "0JNV9-aZOf-O"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "query_engine.query(\n",
        "    \"show a line chart for total sales by invoice year\",\n",
        ");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 553
        },
        "id": "a1Cpso26Owdf",
        "outputId": "6c6fe85a-6de2-4887-e8e6-5939db1a1f0d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df.groupby('InvoiceYear')['Sales'].sum().plot(kind='line')\n",
            "```\n",
            "> Pandas Output: Axes(0.125,0.11;0.775x0.77)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from statsmodels.tsa.seasonal import seasonal_decompose\n",
        "import statsmodels.api as sm\n",
        "import pandas as pd\n",
        "\n",
        "query_engine.query(\n",
        "    \"Convert invoice date sales into a time series dataframe, and produce an ACF plot from statsmodels library\",\n",
        ");"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Gri5ZS0PO3rq",
        "outputId": "7222c940-eadd-46eb-b671-bbae9695058c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> Pandas Instructions:\n",
            "```\n",
            "df['InvoiceDate'] = pd.to_datetime(df['InvoiceDate'])\n",
            "time_series_df = df.set_index('InvoiceDate')['Sales']\n",
            "from statsmodels.graphics.tsaplots import plot_acf\n",
            "plot_acf(time_series_df)\n",
            "\n",
            "```\n",
            "> Pandas Output: There was an error running the output as Python code. Error message: name 'pd' is not defined\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/llama_index/core/query_engine/pandas/output_parser.py\", line 41, in default_output_processor\n",
            "    safe_exec(ast.unparse(module), {}, local_vars)  # type: ignore\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/llama_index/core/exec_utils.py\", line 152, in safe_exec\n",
            "    return exec(__source, _get_restricted_globals(__globals), __locals)\n",
            "  File \"<string>\", line 1, in <module>\n",
            "NameError: name 'pd' is not defined\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "2UpYg2noQBzu"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df['InvoiceDate'] = pd.to_datetime(df['InvoiceDate'])\n",
        "time_series_df = df.set_index('InvoiceDate')['Sales']\n",
        "from statsmodels.graphics.tsaplots import plot_acf\n",
        "plot_acf(time_series_df);"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 473
        },
        "id": "UMpv0eizP9Sg",
        "outputId": "3fc876dc-d5cf-4099-9a00-dc11e7192657"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "spH4hUAnQb7s"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}