Finetune_OpenAI_Models_using_In_Context_Learning(ICL)_.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "machine_shape": "hm",
      "authorship_tag": "ABX9TyMX3N3CFHy3xT7BtX1MhRgb",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "TPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Praveen76/Conversation-AI-System-using-LLMs-on-E-commerce-Data/blob/main/Finetune_OpenAI_Models_using_In_Context_Learning(ICL)_.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# !pip install tensorflow==2.8.1\n",
        "!pip install --upgrade tensorflow\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YajjqOPufch-",
        "outputId": "31bff3e6-80f1-45b3-fae6-d633c52ac72f"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.10/dist-packages (2.12.0)\n",
            "Collecting tensorflow\n",
            "  Downloading tensorflow-2.15.0.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (475.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m475.2/475.2 MB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=23.5.26 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.5.26)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.4.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.9.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (16.0.6)\n",
            "Requirement already satisfied: ml-dtypes~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.23.5)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from tensorflow) (23.2)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (3.20.3)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from tensorflow) (67.7.2)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.16.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (2.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (4.9.0)\n",
            "Requirement already satisfied: wrapt<1.15,>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.14.1)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (0.36.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow) (1.60.1)\n",
            "Collecting tensorboard<2.16,>=2.15 (from tensorflow)\n",
            "  Downloading tensorboard-2.15.2-py3-none-any.whl (5.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m48.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tensorflow-estimator<2.16,>=2.15.0 (from tensorflow)\n",
            "  Downloading tensorflow_estimator-2.15.0-py2.py3-none-any.whl (441 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m442.0/442.0 kB\u001b[0m \u001b[31m40.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting keras<2.16,>=2.15.0 (from tensorflow)\n",
            "  Downloading keras-2.15.0-py3-none-any.whl (1.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m54.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from astunparse>=1.6.0->tensorflow) (0.42.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (2.17.3)\n",
            "Collecting google-auth-oauthlib<2,>=0.5 (from tensorboard<2.16,>=2.15->tensorflow)\n",
            "  Downloading google_auth_oauthlib-1.2.0-py2.py3-none-any.whl (24 kB)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.5.2)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (2.31.0)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow) (3.0.1)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (5.3.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (1.3.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow) (2024.2.2)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard<2.16,>=2.15->tensorflow) (2.1.5)\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<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow) (0.5.1)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow) (3.2.2)\n",
            "Installing collected packages: tensorflow-estimator, keras, google-auth-oauthlib, tensorboard, tensorflow\n",
            "  Attempting uninstall: tensorflow-estimator\n",
            "    Found existing installation: tensorflow-estimator 2.12.0\n",
            "    Uninstalling tensorflow-estimator-2.12.0:\n",
            "      Successfully uninstalled tensorflow-estimator-2.12.0\n",
            "  Attempting uninstall: keras\n",
            "    Found existing installation: keras 2.12.0\n",
            "    Uninstalling keras-2.12.0:\n",
            "      Successfully uninstalled keras-2.12.0\n",
            "  Attempting uninstall: google-auth-oauthlib\n",
            "    Found existing installation: google-auth-oauthlib 0.4.6\n",
            "    Uninstalling google-auth-oauthlib-0.4.6:\n",
            "      Successfully uninstalled google-auth-oauthlib-0.4.6\n",
            "  Attempting uninstall: tensorboard\n",
            "    Found existing installation: tensorboard 2.12.0\n",
            "    Uninstalling tensorboard-2.12.0:\n",
            "      Successfully uninstalled tensorboard-2.12.0\n",
            "  Attempting uninstall: tensorflow\n",
            "    Found existing installation: tensorflow 2.12.0\n",
            "    Uninstalling tensorflow-2.12.0:\n",
            "      Successfully uninstalled tensorflow-2.12.0\n",
            "Successfully installed google-auth-oauthlib-1.2.0 keras-2.15.0 tensorboard-2.15.2 tensorflow-2.15.0.post1 tensorflow-estimator-2.15.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install kaggle\n",
        "!pip install xlsxwriter\n",
        "\n",
        "!pip install transformers\n",
        "!pip install datasets\n",
        "!pip install transformers[sentencepiece] datasets\n",
        "!pip install sentencepiece\n",
        "!pip install openai cohere tiktoken"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uOPR6ZQdgnlt",
        "outputId": "4c5e94e9-f8d4-4943-826a-79e0142f96a6"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: kaggle in /usr/local/lib/python3.10/dist-packages (1.5.16)\n",
            "Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.10/dist-packages (from kaggle) (1.16.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from kaggle) (2024.2.2)\n",
            "Requirement already satisfied: python-dateutil in /usr/local/lib/python3.10/dist-packages (from kaggle) (2.8.2)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from kaggle) (2.31.0)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from kaggle) (4.66.1)\n",
            "Requirement already satisfied: python-slugify in /usr/local/lib/python3.10/dist-packages (from kaggle) (8.0.3)\n",
            "Requirement already satisfied: urllib3 in /usr/local/lib/python3.10/dist-packages (from kaggle) (2.0.7)\n",
            "Requirement already satisfied: bleach in /usr/local/lib/python3.10/dist-packages (from kaggle) (6.1.0)\n",
            "Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from bleach->kaggle) (0.5.1)\n",
            "Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.10/dist-packages (from python-slugify->kaggle) (1.3)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->kaggle) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->kaggle) (3.6)\n",
            "Collecting xlsxwriter\n",
            "  Downloading XlsxWriter-3.1.9-py3-none-any.whl (154 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.8/154.8 kB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: xlsxwriter\n",
            "Successfully installed xlsxwriter-3.1.9\n",
            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\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,>=0.16.4 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) (1.23.5)\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) (0.15.1)\n",
            "Requirement already satisfied: safetensors>=0.3.1 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) (4.66.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.16.4->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,>=0.16.4->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",
            "Collecting datasets\n",
            "  Downloading datasets-2.17.0-py3-none-any.whl (536 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.6/536.6 kB\u001b[0m \u001b[31m3.6 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 datasets) (3.13.1)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.23.5)\n",
            "Collecting pyarrow>=12.0.0 (from datasets)\n",
            "  Downloading pyarrow-15.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (38.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m29.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n",
            "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
            "  Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n",
            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.1)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n",
            "Collecting multiprocess (from datasets)\n",
            "  Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m14.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: fsspec[http]<=2023.10.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.3)\n",
            "Requirement already satisfied: huggingface-hub>=0.19.4 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.20.3)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.2)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.4->datasets) (4.9.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
            "Installing collected packages: pyarrow, dill, multiprocess, datasets\n",
            "  Attempting uninstall: pyarrow\n",
            "    Found existing installation: pyarrow 10.0.1\n",
            "    Uninstalling pyarrow-10.0.1:\n",
            "      Successfully uninstalled pyarrow-10.0.1\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "ibis-framework 7.1.0 requires pyarrow<15,>=2, but you have pyarrow 15.0.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed datasets-2.17.0 dill-0.3.8 multiprocess-0.70.16 pyarrow-15.0.0\n",
            "Requirement already satisfied: transformers[sentencepiece] in /usr/local/lib/python3.10/dist-packages (4.35.2)\n",
            "Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (2.17.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (3.13.1)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (0.20.3)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (1.23.5)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (23.2)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (6.0.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (2023.12.25)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (2.31.0)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (0.15.1)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (0.4.2)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (4.66.1)\n",
            "Requirement already satisfied: sentencepiece!=0.1.92,>=0.1.91 in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (0.1.99)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from transformers[sentencepiece]) (3.20.3)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (15.0.0)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n",
            "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.3.8)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets) (0.70.16)\n",
            "Requirement already satisfied: fsspec[http]<=2023.10.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.3)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.16.4->transformers[sentencepiece]) (4.9.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[sentencepiece]) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[sentencepiece]) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[sentencepiece]) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[sentencepiece]) (2024.2.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.1.99)\n",
            "Collecting openai\n",
            "  Downloading openai-1.12.0-py3-none-any.whl (226 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.7/226.7 kB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting cohere\n",
            "  Downloading cohere-4.46-py3-none-any.whl (52 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m52.2/52.2 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tiktoken\n",
            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m16.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement 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",
            "Collecting httpx<1,>=0.23.0 (from openai)\n",
            "  Downloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (2.6.1)\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) (4.66.1)\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: aiohttp<4.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from cohere) (3.9.3)\n",
            "Collecting backoff<3.0,>=2.0 (from cohere)\n",
            "  Downloading backoff-2.2.1-py3-none-any.whl (15 kB)\n",
            "Collecting fastavro<2.0,>=1.8 (from cohere)\n",
            "  Downloading fastavro-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m46.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting importlib_metadata<7.0,>=6.0 (from cohere)\n",
            "  Downloading importlib_metadata-6.11.0-py3-none-any.whl (23 kB)\n",
            "Requirement already satisfied: requests<3.0.0,>=2.25.0 in /usr/local/lib/python3.10/dist-packages (from cohere) (2.31.0)\n",
            "Requirement already satisfied: urllib3<3,>=1.26 in /usr/local/lib/python3.10/dist-packages (from cohere) (2.0.7)\n",
            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.12.25)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (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,>=3.0->cohere) (4.0.3)\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: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.2.2)\n",
            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n",
            "  Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai)\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib_metadata<7.0,>=6.0->cohere) (3.17.0)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (2.16.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.25.0->cohere) (3.3.2)\n",
            "Installing collected packages: importlib_metadata, h11, fastavro, backoff, tiktoken, httpcore, httpx, cohere, openai\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 backoff-2.2.1 cohere-4.46 fastavro-1.9.3 h11-0.14.0 httpcore-1.0.2 httpx-0.26.0 importlib_metadata-6.11.0 openai-1.12.0 tiktoken-0.6.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "# Print the TensorFlow version\n",
        "print(\"TensorFlow version:\", tf.__version__)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Q212OD4TAsyj",
        "outputId": "b6c6e0fb-f96d-4800-b3a7-aaf3058368cf"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "TensorFlow version: 2.15.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import openai as OpenAI\n",
        "\n",
        "# Print the TensorFlow version\n",
        "print(\"OpenAI version:\", OpenAI.__version__)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XKV84uhzaRpy",
        "outputId": "4663861a-8699-423b-ed4d-bb5f750a4a38"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "OpenAI version: 1.12.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Basic Libraries\n",
        "import os\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "#Visualization Libraries\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "#Text Handling Libraries\n",
        "import re\n",
        "from sklearn.metrics.pairwise import cosine_similarity\n",
        "from sklearn.feature_extraction.text import CountVectorizer\n",
        "import xlsxwriter\n",
        "import scipy.spatial\n",
        "import datetime\n",
        "\n",
        "from datasets import load_dataset\n",
        "from transformers import pipeline\n",
        "\n",
        "import tqdm\n"
      ],
      "metadata": {
        "id": "i8nmIrCUzMj3"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "HD8Jm9NLe5bI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "#### Code to mount G-Drive####\n",
        "from google.colab import drive\n",
        "\n",
        "drive.mount('/content/drive/', force_remount=True)\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "0cm04ZUr-LFE",
        "outputId": "323a8c76-7cbe-4a6d-bd4b-ae3325ebd67b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive/\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import yaml\n",
        "import json\n",
        "import openai\n",
        "\n",
        "# Load relevant API Keys\n",
        "file_path = '/content/drive/MyDrive/.API_KEYS/API_KEYS.yml'\n",
        "\n",
        "with open(file_path, 'r') as file:\n",
        "    api_keys = yaml.safe_load(file)\n",
        "\n",
        "\n",
        "# Extract OPEN_AI key\n",
        "api_key = api_keys['OPEN_AI']['Key']\n",
        "\n",
        "openai.api_key = api_key\n",
        "\n"
      ],
      "metadata": {
        "id": "z5DVY0mU9FI8"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%pwd"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "GpFF6p2Rk_X2",
        "outputId": "1d14256c-1039-4d60-8676-85e7d41705c5"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/content'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!git clone https://github.com/Praveen76/Conversation-AI-System-using-LLMs-on-E-commerce-Data.git"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xlQF9G4ie2xQ",
        "outputId": "e348528c-68eb-4395-f63a-3716204b6f0f"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'Conversation-AI-System-using-LLMs-on-E-commerce-Data'...\n",
            "remote: Enumerating objects: 74, done.\u001b[K\n",
            "remote: Counting objects: 100% (74/74), done.\u001b[K\n",
            "remote: Compressing objects: 100% (74/74), done.\u001b[K\n",
            "remote: Total 74 (delta 40), reused 5 (delta 0), pack-reused 0\u001b[K\n",
            "Receiving objects: 100% (74/74), 11.21 MiB | 29.96 MiB/s, done.\n",
            "Resolving deltas: 100% (40/40), done.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%cd Conversation-AI-System-using-LLMs-on-E-commerce-Data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WsTkpr5ghiS2",
        "outputId": "a9afd0c3-4a3f-4ce1-9792-cf2d9d0c8d8e"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/Conversation-AI-System-using-LLMs-on-E-commerce-Data\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load Data\n",
        "df = pd.read_csv(\"./data.csv\")"
      ],
      "metadata": {
        "id": "FvyU4F_S0qeY"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "vk9MPAeLEbmY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Benchmark 1 :: Generate Questions\n",
        "\n",
        "Since we don't have questions in our dataset. Hence, we'll use GPT3.5-x to generate questions, which customers could ask to an autonomous agent, for us.\n"
      ],
      "metadata": {
        "id": "9TbrfvupQUgz"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "# # ############################################## Generate Questions #########################33\n",
        "import tqdm\n",
        "tqdm.pandas()\n",
        "\n",
        "# # # Create two datetime objects\n",
        "# start_time = datetime.datetime.now()\n",
        "\n",
        "# df['Ques']=0\n",
        "# Ques={}\n",
        "# prompt = f\"Generate 1 question from the following text:\\n{row.ProdDescr}\\nQuestions:\"\n",
        "\n",
        "# # Generate questions for each record of dataset\n",
        "# for index, row in df.iterrows():\n",
        "\n",
        "#     # Request to the OpenAI API\n",
        "#     response = openai.completions.create(\n",
        "#         model=\"gpt-3.5-turbo-instruct\",  # You can experiment with different engines\n",
        "#         prompt=prompt,\n",
        "#         max_tokens=50,  # Adjust this based on the expected length of the questions\n",
        "#     )\n",
        "\n",
        "#     # Extract the generated questions from the API response\n",
        "#     generated_question = response.choices[0].text.strip()\n",
        "#     Ques[index]=generated_question\n",
        "\n",
        "# end_time = datetime.datetime.now()\n",
        "\n",
        "# # Calculate the time difference in seconds\n",
        "# time_difference = (end_time - start_time).total_seconds()\n",
        "\n",
        "# print(\"The time difference is:\", round((time_difference/60),2), \"mnts\")"
      ],
      "metadata": {
        "id": "pz156kheoMaC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# df.Ques = 0\n",
        "\n",
        "# # Iterate through items\n",
        "# for key, ques in Ques.items():\n",
        "#   df.loc[key,'Ques']=ques\n"
      ],
      "metadata": {
        "id": "nIkN32n42oHC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# df.to_csv(\"ConvAIAns.csv\",index=False)"
      ],
      "metadata": {
        "id": "f5XbLXwanzdv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# df = pd.read_csv(\"ConvAIQues.csv\")\n"
      ],
      "metadata": {
        "id": "hm_koYH0avuX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "UKiq5e0sQyjx"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Benchmark 2 :: Generate Answers\n",
        "\n",
        "Since we don't have answers, which the autonomous agent would give to customers' queries, in our dataset. Hence, we'll use GPT3.5-x to generate answers. We'll use these answers as a benchmark or reference text to validate responses generated from fine-tuned Open source LLMs such Llama, T5, etc.\n"
      ],
      "metadata": {
        "id": "1O6N5Nm-QzbU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "################# Create Benchmark for answers using GPT-3.5-turbo-instruct #################\n",
        "# Create two datetime objects\n",
        "start_time = datetime.datetime.now()\n",
        "df['Anws'] = 0\n",
        "def answer_questions(question, context):\n",
        "    prompt = f\"You're a chatbot on an E-commerce platform answering customers' questions. \\\n",
        "              Please make sure to provide a complete sentence that ends with a period.\\\n",
        "              Your response should be at least 1 sentence long and no longer than 3 sentences :\\n Question: {question}\\nContext: {context}\\nAnswer:\"\n",
        "\n",
        "\n",
        "    response = openai.completions.create(\n",
        "        model=\"gpt-3.5-turbo-instruct\",\n",
        "        prompt=prompt,\n",
        "        max_tokens=100,\n",
        "        n=1,  # Generate one completion per prompt\n",
        "        stop=None,\n",
        "        temperature=0.5,\n",
        "        frequency_penalty=0.5,\n",
        "        presence_penalty=0.5,\n",
        "        best_of=1,\n",
        "    )\n",
        "    answer = response.choices[0].text.strip()\n",
        "    return answer\n",
        "\n",
        "# Use vectorized operations instead of looping through rows\n",
        "df['Anws'] = df.apply(lambda row: answer_questions(row['Ques'], row['ProdDescr']), axis=1)\n",
        "\n",
        "\n",
        "end_time = datetime.datetime.now()\n",
        "\n",
        "# Calculate the time difference in seconds\n",
        "time_difference = (end_time - start_time).total_seconds()\n",
        "\n",
        "print(\"The time difference is:\", round((time_difference/60), 2))\n"
      ],
      "metadata": {
        "id": "pDjCGKJVnzPf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "\n",
        "1. `max_tokens`: It limits the length of the generated completion by specifying the maximum number of tokens (words or characters) the response should have. In this example, it's set to 100 tokens.\n",
        "\n",
        "2. `n`: It represents the number of completions to generate for a given prompt. Here, it's set to 1, meaning it will generate only one completion per prompt.\n",
        "\n",
        "3. `stop`: This parameter allows you to specify a list of strings to signal the model to stop generating tokens when any of these strings are encountered. In this case, it's set to `None`, meaning there is no predefined stop condition.\n",
        "\n",
        "4. `temperature`: It controls the randomness of the generated output. A higher value (e.g., 1.0) makes the output more creative and diverse, while a lower value (e.g., 0.1) makes it more focused and deterministic. Here, it's set to 0.5.\n",
        "\n",
        "5. `frequency_penalty`: This parameter influences the model to avoid generating repetitive phrases. A higher penalty (e.g., 0.8) reduces the likelihood of repetitive output. Here, it's set to 0.5.\n",
        "\n",
        "6. `presence_penalty`: Similar to `frequency_penalty`, this parameter influences the model to avoid generating content that was present in the input prompt. A higher penalty (e.g., 0.8) reduces the likelihood of regurgitating input. Here, it's set to 0.5.\n",
        "\n",
        "7. `best_of`: It specifies the number of completions to generate and then return the best one. In this case, it's set to 1, meaning it will return the best completion out of a single attempt.\n"
      ],
      "metadata": {
        "id": "mYu9KGATp02l"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df.head(2)"
      ],
      "metadata": {
        "id": "t1j3yXwiURlr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "4H6b4FTKskjP"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "4bv9U0s-vzcK"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Benchmark 3 :: Generate Summary\n",
        "\n",
        "Since we don't have summaries, which the autonomous agent would give to from product descriptions, in our dataset. Hence, we'll use GPT3.5-x to generate summaries. We'll use these summaries as a benchmark or reference text to validate responses generated from fine-tuned Open source LLMs such Llama, T5, etc.\n"
      ],
      "metadata": {
        "id": "c-jf-4K5RPeb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "####################################### GPT-3.5-turbo-instruct model: Benchmark for Summarization of Product descriptions ##########################\n",
        "\n",
        "# Function to summarize text using the GPT-3 model\n",
        "\n",
        "from tqdm import tqdm\n",
        "import openai\n",
        "\n",
        "# Function to summarize text using the GPT-3 model\n",
        "def summarize_text(input_text, max_tokens=100):\n",
        "    response = openai.completions.create(\n",
        "        model=\"gpt-3.5-turbo-instruct\",\n",
        "        prompt=f\"You're a chatbot on an E-commerce platform, and you need to summarize product descriptions to customers.\\\n",
        "               Your response should be at least 1 sentence long and no longer than 3 sentences.\\\n",
        "                Summarize the following text:\\n{input_text}\\nSummary:\",\n",
        "        max_tokens=100,  # Adjust max_tokens as per your needs\n",
        "        n=1,  # Number of completions to generate\n",
        "        stop=None,\n",
        "        temperature=0.5,\n",
        "        frequency_penalty=0.5,\n",
        "        presence_penalty=0.5,\n",
        "        best_of=1,\n",
        "    )\n",
        "    summary = response.choices[0].text.strip()\n",
        "    return summary\n",
        "\n",
        "# Create a tqdm instance with the total number of rows in the DataFrame\n",
        "tqdm_pandas = tqdm(total=len(df), position=0, leave=True)\n",
        "\n",
        "# Iterate over DataFrame rows with tqdm\n",
        "for index, row in df.iterrows():\n",
        "    summary = summarize_text(row['ProdDescr'])\n",
        "    df.at[index, 'GPTSumm'] = summary\n",
        "\n",
        "    # Update tqdm progress bar\n",
        "    tqdm_pandas.update(1)\n",
        "\n",
        "# Close tqdm progress bar\n",
        "tqdm_pandas.close()\n"
      ],
      "metadata": {
        "id": "1qXkcQmT4gsR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0983e983-6a0c-4fe6-b14e-011a277aae25"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            " 69%|██████▊   | 510/743 [07:24<03:58,  1.02s/it]"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.to_csv(\"GPTSumm_Updated.csv\",index=False)"
      ],
      "metadata": {
        "id": "Itjut3tc-syC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load Data\n",
        "df = pd.read_csv(\"./GPTSumm_Updated.csv\")"
      ],
      "metadata": {
        "id": "pa-7GCeR_uIV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head(2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 404
        },
        "id": "v7nQP5euBLDr",
        "outputId": "09a745c2-d3a1-4abf-c406-5b7c687e63ef"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   product_id                                           ProdName  \\\n",
              "0  B008IFXQFU  TP-Link USB WiFi Adapter for PC(TL-WN725N), N1...   \n",
              "1  B08WRBG3XW  boAt Type C A325 Tangle-free, Sturdy Type C Ca...   \n",
              "\n",
              "                                            category  DPrice APrice DPerct  \\\n",
              "0  Computers&Accessories|NetworkingDevices|Networ...     499   ₹999    50%   \n",
              "1  Computers&Accessories|Accessories&Peripherals|...     199   ₹499    60%   \n",
              "\n",
              "   rating                                          ProdDescr  \\\n",
              "0     4.2  USB WiFi Adapter —— Speedy wireless transmissi...   \n",
              "1     4.1  Type C A 325 Cable Is Designed With A Perfect ...   \n",
              "\n",
              "                                                 UID  \\\n",
              "0  AGV3IEFANZCKECFGUM42MRH5FNOA,AEBO7NWCNXKT4AESA...   \n",
              "1  AFB5KJR4Q5FICAHBOPDPUTB3O7QQ,AHW3QBHDOUMXODZ4E...   \n",
              "\n",
              "                                               UName  ...  \\\n",
              "0  Azhar JuMan,Anirudh Sood,Hari Krishnan PS,Akas...  ...   \n",
              "1  Rohan Narkar,JAGWINDER SINGH,Gursewak Singh,Av...  ...   \n",
              "\n",
              "           Subcategory rBucket DPBucket  \\\n",
              "0  WirelessUSBAdapters      HR      Low   \n",
              "1            USBCables      HR      Low   \n",
              "\n",
              "         product_classification_features          label  score  \\\n",
              "0  B008IFXQFU Low HR WirelessUSBAdapters  Very Positive  48.18   \n",
              "1            B08WRBG3XW Low HR USBCables  Very Positive  60.78   \n",
              "\n",
              "                                                Ques  \\\n",
              "0  What are the different uses for this multi-pur...   \n",
              "1  What are some suggested uses for this multi-pu...   \n",
              "\n",
              "                                                Anws BERT_Ans  \\\n",
              "0  The multi-purpose LED light can be used for va...        0   \n",
              "1  The multi-purpose LED night light can be used ...        0   \n",
              "\n",
              "                                             GPTSumm  \n",
              "0  This USB WiFi adapter offers speedy wireless t...  \n",
              "1  The Type C A 325 Cable is a durable and versat...  \n",
              "\n",
              "[2 rows x 25 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d6057f0b-18e8-4fdf-9f8c-dce5e6bca694\" 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>product_id</th>\n",
              "      <th>ProdName</th>\n",
              "      <th>category</th>\n",
              "      <th>DPrice</th>\n",
              "      <th>APrice</th>\n",
              "      <th>DPerct</th>\n",
              "      <th>rating</th>\n",
              "      <th>ProdDescr</th>\n",
              "      <th>UID</th>\n",
              "      <th>UName</th>\n",
              "      <th>...</th>\n",
              "      <th>Subcategory</th>\n",
              "      <th>rBucket</th>\n",
              "      <th>DPBucket</th>\n",
              "      <th>product_classification_features</th>\n",
              "      <th>label</th>\n",
              "      <th>score</th>\n",
              "      <th>Ques</th>\n",
              "      <th>Anws</th>\n",
              "      <th>BERT_Ans</th>\n",
              "      <th>GPTSumm</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>B008IFXQFU</td>\n",
              "      <td>TP-Link USB WiFi Adapter for PC(TL-WN725N), N1...</td>\n",
              "      <td>Computers&amp;Accessories|NetworkingDevices|Networ...</td>\n",
              "      <td>499</td>\n",
              "      <td>₹999</td>\n",
              "      <td>50%</td>\n",
              "      <td>4.2</td>\n",
              "      <td>USB WiFi Adapter —— Speedy wireless transmissi...</td>\n",
              "      <td>AGV3IEFANZCKECFGUM42MRH5FNOA,AEBO7NWCNXKT4AESA...</td>\n",
              "      <td>Azhar JuMan,Anirudh Sood,Hari Krishnan PS,Akas...</td>\n",
              "      <td>...</td>\n",
              "      <td>WirelessUSBAdapters</td>\n",
              "      <td>HR</td>\n",
              "      <td>Low</td>\n",
              "      <td>B008IFXQFU Low HR WirelessUSBAdapters</td>\n",
              "      <td>Very Positive</td>\n",
              "      <td>48.18</td>\n",
              "      <td>What are the different uses for this multi-pur...</td>\n",
              "      <td>The multi-purpose LED light can be used for va...</td>\n",
              "      <td>0</td>\n",
              "      <td>This USB WiFi adapter offers speedy wireless t...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>B08WRBG3XW</td>\n",
              "      <td>boAt Type C A325 Tangle-free, Sturdy Type C Ca...</td>\n",
              "      <td>Computers&amp;Accessories|Accessories&amp;Peripherals|...</td>\n",
              "      <td>199</td>\n",
              "      <td>₹499</td>\n",
              "      <td>60%</td>\n",
              "      <td>4.1</td>\n",
              "      <td>Type C A 325 Cable Is Designed With A Perfect ...</td>\n",
              "      <td>AFB5KJR4Q5FICAHBOPDPUTB3O7QQ,AHW3QBHDOUMXODZ4E...</td>\n",
              "      <td>Rohan Narkar,JAGWINDER SINGH,Gursewak Singh,Av...</td>\n",
              "      <td>...</td>\n",
              "      <td>USBCables</td>\n",
              "      <td>HR</td>\n",
              "      <td>Low</td>\n",
              "      <td>B08WRBG3XW Low HR USBCables</td>\n",
              "      <td>Very Positive</td>\n",
              "      <td>60.78</td>\n",
              "      <td>What are some suggested uses for this multi-pu...</td>\n",
              "      <td>The multi-purpose LED night light can be used ...</td>\n",
              "      <td>0</td>\n",
              "      <td>The Type C A 325 Cable is a durable and versat...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2 rows × 25 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-d6057f0b-18e8-4fdf-9f8c-dce5e6bca694')\"\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-d6057f0b-18e8-4fdf-9f8c-dce5e6bca694 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-d6057f0b-18e8-4fdf-9f8c-dce5e6bca694');\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-2fec5f01-2c25-4911-881a-d1a62d11e173\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-2fec5f01-2c25-4911-881a-d1a62d11e173')\"\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-2fec5f01-2c25-4911-881a-d1a62d11e173 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.columns"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QWPh1DG1D-At",
        "outputId": "531a5b47-a9b6-4e17-aa33-b8ce244f98bf"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['product_id', 'ProdName', 'category', 'DPrice', 'APrice', 'DPerct',\n",
              "       'rating', 'ProdDescr', 'UID', 'UName', 'review_id', 'review_title',\n",
              "       'review_content', 'img_link', 'ProdLink', 'Subcategory', 'rBucket',\n",
              "       'DPBucket', 'product_classification_features', 'label', 'score', 'Ques',\n",
              "       'Anws', 'BERT_Ans', 'GPTSumm'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "1CsDjg0LRjtD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "summaries"
      ],
      "metadata": {
        "id": "1_J5YtsWRkei"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Benchmark 3 :: Sentiment Analysis\n",
        "\n",
        "Since we don't have labels for customers' reviews in our dataset. Hence, we'll use GPT3.5-x to generate labels for these product reviews. We'll use these labels as a benchmark or reference text to validate labels generated from fine-tuned Open source LLMs such Llama, T5, BERT, etc.\n"
      ],
      "metadata": {
        "id": "rLGaId_LRnNk"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Method 1: Prefix- Training:"
      ],
      "metadata": {
        "id": "H3qLL_qaLKZ-"
      }
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "Zcc14iRALJtu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "######## Benchmark for Sentiment Analysis using GPT 3.5 ##########################\n",
        "# pip install openai\n",
        "\n",
        "import openai\n",
        "from tqdm import tqdm  # Import tqdm correctly\n",
        "\n",
        "\n",
        "def analyze_sentiment(text):\n",
        "    try:\n",
        "        # Define the prompt for sentiment analysis\n",
        "        prompt = f\"Analyze the sentiment of the following text and output either Positive, Negative, or Neutral:\\n\\n{text}\\n\\nSentiment:\"\n",
        "\n",
        "        # Call the GPT-3 API for sentiment analysis\n",
        "        response = openai.completions.create(\n",
        "            model=\"gpt-3.5-turbo-instruct\",\n",
        "            prompt=prompt,\n",
        "            max_tokens=50,  # Adjust as needed\n",
        "            temperature=0.7,  # Higher values make output more random\n",
        "            best_of=1,\n",
        "        )\n",
        "\n",
        "        # Extract the sentiment label (Positive, Negative, or Neutral)\n",
        "        sentiment = response.choices[0].text.strip()\n",
        "        return sentiment\n",
        "\n",
        "    except Exception as e:\n",
        "        return f\"Error analyzing sentiment: {str(e)}\"\n",
        "\n",
        "\n",
        "# Create a tqdm instance with the total number of rows in the DataFrame\n",
        "tqdm_pandas = tqdm(total=len(df), position=0, leave=True)\n",
        "\n",
        "# Iterate over DataFrame rows with tqdm\n",
        "for index, row in df.iterrows():\n",
        "    summary = analyze_sentiment(row['review_content'])\n",
        "    df.at[index, 'Sentiment'] = summary\n",
        "\n",
        "    # Update tqdm progress bar\n",
        "    tqdm_pandas.update(1)\n",
        "\n",
        "# Close tqdm progress bar\n",
        "tqdm_pandas.close()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lssW4Gs_C89n",
        "outputId": "737dd556-ccc0-4b24-ec02-9055d6a39eb2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 743/743 [02:08<00:00,  5.79it/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "sentiments = ['Positive','Negative', 'Neutral']\n",
        "df = df[df.Sentiment.isin(sentiments)]\n",
        "df.Sentiment.value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IrDJET4UFFrt",
        "outputId": "1297cdba-4029-4826-a1c6-134fada76c96"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Positive    562\n",
              "Negative     91\n",
              "Neutral      81\n",
              "Name: Sentiment, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "NKBnqRqrKcB3"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}