notebook-crewai-project-2a345e3e55c5476aa0071ddd60e29914.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "skNPGR0u7hH2",
        "collapsed": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "bcb5d997-9b4b-47d8-c433-4f1ce74d6146"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m68.5/68.5 kB\u001b[0m \u001b[31m1.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.3/55.3 kB\u001b[0m \u001b[31m3.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m975.5/975.5 kB\u001b[0m \u001b[31m15.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.7/194.7 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.2/50.2 kB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.5/327.5 kB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.9/59.9 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m107.0/107.0 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.0/233.0 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m525.5/525.5 kB\u001b[0m \u001b[31m22.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m131.5/131.5 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.6/40.6 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.3/41.3 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m290.4/290.4 kB\u001b[0m \u001b[31m21.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m37.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.6/327.6 kB\u001b[0m \u001b[31m17.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m202.6/202.6 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.1/115.1 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m339.9/339.9 kB\u001b[0m \u001b[31m19.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.4/9.4 MB\u001b[0m \u001b[31m59.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m61.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.9/302.9 kB\u001b[0m \u001b[31m28.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.4/127.4 kB\u001b[0m \u001b[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m163.9/163.9 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m59.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.4/62.4 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m70.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m80.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m6.8 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",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m283.7/283.7 kB\u001b[0m \u001b[31m21.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m38.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m145.0/145.0 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.2/49.2 kB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m202.5/202.5 kB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m198.5/198.5 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.5/196.5 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m342.2/342.2 kB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.3/207.3 kB\u001b[0m \u001b[31m16.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.6/21.6 MB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.0/53.0 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m52.5/52.5 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.5/130.5 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m467.7/467.7 kB\u001b[0m \u001b[31m27.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.6/78.6 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.6/53.6 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m173.8/173.8 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.3/40.3 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m856.7/856.7 kB\u001b[0m \u001b[31m41.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.7/98.7 kB\u001b[0m \u001b[31m9.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m21.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m49.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m32.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m13.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.4/194.4 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m41.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m43.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m139.2/139.2 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m70.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.7/307.7 kB\u001b[0m \u001b[31m25.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m74.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m82.7/82.7 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Building wheel for docx2txt (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
          ]
        }
      ],
      "source": [
        "pip install  crewai  crewai_tools crewai langchain langchain_google-genai -q\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from crewai import Agent, Task, Crew, Process\n",
        "import sys\n"
      ],
      "metadata": {
        "id": "w0VHxXrD9LXT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "import getpass\n",
        "import os\n",
        "\n",
        "if \"GOOGLE_API_KEY\" not in os.environ:\n",
        "    os.environ[\"GOOGLE_API_KEY\"] = getpass.getpass(\"Provide your Google API Key\")"
      ],
      "metadata": {
        "id": "PGHI5NmcOXj3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 329
        },
        "outputId": "a6b4f434-2efa-447f-a345-937459158e99"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "Interrupted by user",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-3-780e8b1c4fb0>\u001b[0m in \u001b[0;36m<cell line: 4>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m\"GOOGLE_API_KEY\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menviron\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m     \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menviron\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"GOOGLE_API_KEY\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetpass\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetpass\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Provide your Google API Key\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36mgetpass\u001b[0;34m(self, prompt, stream)\u001b[0m\n\u001b[1;32m    832\u001b[0m             warnings.warn(\"The `stream` parameter of `getpass.getpass` will have no effect when using ipykernel\",\n\u001b[1;32m    833\u001b[0m                     UserWarning, stacklevel=2)\n\u001b[0;32m--> 834\u001b[0;31m         return self._input_request(prompt,\n\u001b[0m\u001b[1;32m    835\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_ident\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    836\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_header\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36m_input_request\u001b[0;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[1;32m    893\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    894\u001b[0m                 \u001b[0;31m# re-raise KeyboardInterrupt, to truncate traceback\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 895\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Interrupted by user\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    896\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    897\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarning\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Invalid Message:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexc_info\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain_google_genai import ChatGoogleGenerativeAI\n",
        "\n",
        "llm = ChatGoogleGenerativeAI(model=\"gemini-pro\")\n"
      ],
      "metadata": {
        "id": "9syJNYE2PV85"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def get_blog_topic():\n",
        "    return input(\"Enter the topic you want for the blog: \")"
      ],
      "metadata": {
        "id": "N4rPjKayT_PG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "blog_topic = get_blog_topic()\n"
      ],
      "metadata": {
        "id": "hCHbGa7bUDov"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "researcher = Agent(\n",
        "    role=\"Research\",\n",
        "    goal=f\"Research on {blog_topic}\",\n",
        "    backstory=f\"You are an AI bot which is interested in understanding {blog_topic} and will search most relevant information on it.\",\n",
        "    verbose=True,\n",
        "    allow_delegation=False,\n",
        "    llm=llm)"
      ],
      "metadata": {
        "id": "WYTKOhdZUI54"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "writer = Agent(\n",
        "    role=\"writer\",\n",
        "    goal=f\"To write a funny but informative blog post on {blog_topic}\",\n",
        "    backstory=f\"You are an AI Assistant who is really good at writing blogs that are both funny and informative at the same time.\",\n",
        "    verbose=True,\n",
        "    allow_delegation=False,\n",
        "    llm=llm\n",
        ")\n"
      ],
      "metadata": {
        "id": "Kbo5jMv5P0sW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "task1 = Task(\n",
        "    description=f\"Investigate {blog_topic}\",\n",
        "    agent=researcher,\n",
        "    expected_output=f\"Detailed research on {blog_topic}.\"\n",
        ")\n",
        "task2 = Task(\n",
        "    description=f\"Write an interesting blog post about {blog_topic}\",\n",
        "    agent=writer,\n",
        "    expected_output=f\"Engaging blog post explaining {blog_topic} in a simple and relatable way.\"\n",
        ")\n"
      ],
      "metadata": {
        "id": "nmD7IbAZQ2fD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "crew = Crew(\n",
        "    agents=[researcher, writer],\n",
        "    tasks=[task1, task2],\n",
        "    verbose=2,\n",
        "    process=Process.sequential\n",
        ")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-6csDNtCRfaS",
        "outputId": "e745ec61-fac0-4d9c-efc4-13934f3c0398"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:opentelemetry.trace:Overriding of current TracerProvider is not allowed\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "result = crew.kickoff()\n",
        "\n",
        "print(result)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HCw-L-45RkPI",
        "outputId": "67a876a0-3874-4eef-d62d-03ead2886861"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m\u001b[95m [DEBUG]: == Working Agent: Research\u001b[00m\n",
            "\u001b[1m\u001b[95m [INFO]: == Starting Task: Investigate transformers in AI\u001b[00m\n",
            "\n",
            "\n",
            "\u001b[1m> Entering new CrewAgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I now can give a great answer\n",
            "Final Answer: Transformers are a type of neural network that has become increasingly popular in recent years, particularly in the field of natural language processing (NLP). They are based on the encoder-decoder architecture, which allows them to learn the relationship between sequences of data, such as words in a sentence.\n",
            "\n",
            "One of the key advantages of transformers is their ability to handle long-range dependencies. This is important in NLP tasks such as machine translation and text summarization, where the meaning of a word or phrase can be influenced by words that are far away in the sequence. Transformers are able to capture these long-range dependencies by using a self-attention mechanism, which allows each element in the sequence to attend to all other elements.\n",
            "\n",
            "Another advantage of transformers is their ability to parallelize computations. This is important for training large models on large datasets, as it allows the model to be trained on multiple GPUs simultaneously. Transformers are also relatively easy to implement, making them a popular choice for researchers and practitioners alike.\n",
            "\n",
            "Here are some of the specific tasks that transformers have been shown to be effective for:\n",
            "\n",
            "* Machine translation\n",
            "* Text summarization\n",
            "* Question answering\n",
            "* Named entity recognition\n",
            "* Part-of-speech tagging\n",
            "* Language modeling\n",
            "* Speech recognition\n",
            "* Image captioning\n",
            "\n",
            "Transformers are a powerful tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "Here are some of the key challenges that transformers face:\n",
            "\n",
            "* Transformers can be computationally expensive to train, especially for large models.\n",
            "* Transformers can be difficult to interpret, making it difficult to understand how they make decisions.\n",
            "* Transformers can be sensitive to hyperparameters, making it difficult to find the optimal settings for a given task.\n",
            "\n",
            "Despite these challenges, transformers are a promising tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\u001b[1m\u001b[92m [DEBUG]: == [Research] Task output: Transformers are a type of neural network that has become increasingly popular in recent years, particularly in the field of natural language processing (NLP). They are based on the encoder-decoder architecture, which allows them to learn the relationship between sequences of data, such as words in a sentence.\n",
            "\n",
            "One of the key advantages of transformers is their ability to handle long-range dependencies. This is important in NLP tasks such as machine translation and text summarization, where the meaning of a word or phrase can be influenced by words that are far away in the sequence. Transformers are able to capture these long-range dependencies by using a self-attention mechanism, which allows each element in the sequence to attend to all other elements.\n",
            "\n",
            "Another advantage of transformers is their ability to parallelize computations. This is important for training large models on large datasets, as it allows the model to be trained on multiple GPUs simultaneously. Transformers are also relatively easy to implement, making them a popular choice for researchers and practitioners alike.\n",
            "\n",
            "Here are some of the specific tasks that transformers have been shown to be effective for:\n",
            "\n",
            "* Machine translation\n",
            "* Text summarization\n",
            "* Question answering\n",
            "* Named entity recognition\n",
            "* Part-of-speech tagging\n",
            "* Language modeling\n",
            "* Speech recognition\n",
            "* Image captioning\n",
            "\n",
            "Transformers are a powerful tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "Here are some of the key challenges that transformers face:\n",
            "\n",
            "* Transformers can be computationally expensive to train, especially for large models.\n",
            "* Transformers can be difficult to interpret, making it difficult to understand how they make decisions.\n",
            "* Transformers can be sensitive to hyperparameters, making it difficult to find the optimal settings for a given task.\n",
            "\n",
            "Despite these challenges, transformers are a promising tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "\u001b[00m\n",
            "\u001b[1m\u001b[95m [DEBUG]: == Working Agent: writer\u001b[00m\n",
            "\u001b[1m\u001b[95m [INFO]: == Starting Task: Write an interesting blog post about transformers in AI\u001b[00m\n",
            "\n",
            "\n",
            "\u001b[1m> Entering new CrewAgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I now can give a great answer\n",
            "Final Answer: \n",
            "**Transformers: The Robots That Are Revolutionizing AI**\n",
            "\n",
            "Transformers are a type of neural network that has taken the AI world by storm in recent years. They're particularly good at handling sequential data, such as text and speech, and they've achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks, including machine translation, text summarization, and question answering.\n",
            "\n",
            "But what exactly are transformers, and how do they work?\n",
            "\n",
            "**The Basics of Transformers**\n",
            "\n",
            "Transformers are based on the encoder-decoder architecture. The encoder converts the input sequence into a fixed-length vector, and the decoder then uses this vector to generate the output sequence.\n",
            "\n",
            "The key innovation in transformers is the self-attention mechanism. This mechanism allows each element in the input sequence to attend to all other elements, regardless of their distance. This is important because it allows transformers to capture long-range dependencies in the data.\n",
            "\n",
            "**Advantages of Transformers**\n",
            "\n",
            "Transformers offer several advantages over traditional neural networks:\n",
            "\n",
            "* **They can handle long-range dependencies.** This is important for NLP tasks such as machine translation and text summarization, where the meaning of a word or phrase can be influenced by words that are far away in the sequence.\n",
            "* **They can parallelize computations.** This is important for training large models on large datasets, as it allows the model to be trained on multiple GPUs simultaneously.\n",
            "* **They are relatively easy to implement.** This makes them a popular choice for researchers and practitioners alike.\n",
            "\n",
            "**Applications of Transformers**\n",
            "\n",
            "Transformers have been used to achieve state-of-the-art results on a wide range of NLP tasks, including:\n",
            "\n",
            "* Machine translation\n",
            "* Text summarization\n",
            "* Question answering\n",
            "* Named entity recognition\n",
            "* Part-of-speech tagging\n",
            "* Language modeling\n",
            "* Speech recognition\n",
            "* Image captioning\n",
            "\n",
            "Transformers are a powerful tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "**Challenges of Transformers**\n",
            "\n",
            "Despite their advantages, transformers also face some challenges:\n",
            "\n",
            "* **They can be computationally expensive to train.** This is especially true for large models.\n",
            "* **They can be difficult to interpret.** This makes it difficult to understand how they make decisions.\n",
            "* **They can be sensitive to hyperparameters.** This makes it difficult to find the optimal settings for a given task.\n",
            "\n",
            "Despite these challenges, transformers are a promising tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\u001b[1m\u001b[92m [DEBUG]: == [writer] Task output: **Transformers: The Robots That Are Revolutionizing AI**\n",
            "\n",
            "Transformers are a type of neural network that has taken the AI world by storm in recent years. They're particularly good at handling sequential data, such as text and speech, and they've achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks, including machine translation, text summarization, and question answering.\n",
            "\n",
            "But what exactly are transformers, and how do they work?\n",
            "\n",
            "**The Basics of Transformers**\n",
            "\n",
            "Transformers are based on the encoder-decoder architecture. The encoder converts the input sequence into a fixed-length vector, and the decoder then uses this vector to generate the output sequence.\n",
            "\n",
            "The key innovation in transformers is the self-attention mechanism. This mechanism allows each element in the input sequence to attend to all other elements, regardless of their distance. This is important because it allows transformers to capture long-range dependencies in the data.\n",
            "\n",
            "**Advantages of Transformers**\n",
            "\n",
            "Transformers offer several advantages over traditional neural networks:\n",
            "\n",
            "* **They can handle long-range dependencies.** This is important for NLP tasks such as machine translation and text summarization, where the meaning of a word or phrase can be influenced by words that are far away in the sequence.\n",
            "* **They can parallelize computations.** This is important for training large models on large datasets, as it allows the model to be trained on multiple GPUs simultaneously.\n",
            "* **They are relatively easy to implement.** This makes them a popular choice for researchers and practitioners alike.\n",
            "\n",
            "**Applications of Transformers**\n",
            "\n",
            "Transformers have been used to achieve state-of-the-art results on a wide range of NLP tasks, including:\n",
            "\n",
            "* Machine translation\n",
            "* Text summarization\n",
            "* Question answering\n",
            "* Named entity recognition\n",
            "* Part-of-speech tagging\n",
            "* Language modeling\n",
            "* Speech recognition\n",
            "* Image captioning\n",
            "\n",
            "Transformers are a powerful tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "**Challenges of Transformers**\n",
            "\n",
            "Despite their advantages, transformers also face some challenges:\n",
            "\n",
            "* **They can be computationally expensive to train.** This is especially true for large models.\n",
            "* **They can be difficult to interpret.** This makes it difficult to understand how they make decisions.\n",
            "* **They can be sensitive to hyperparameters.** This makes it difficult to find the optimal settings for a given task.\n",
            "\n",
            "Despite these challenges, transformers are a promising tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "\u001b[00m\n",
            "**Transformers: The Robots That Are Revolutionizing AI**\n",
            "\n",
            "Transformers are a type of neural network that has taken the AI world by storm in recent years. They're particularly good at handling sequential data, such as text and speech, and they've achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks, including machine translation, text summarization, and question answering.\n",
            "\n",
            "But what exactly are transformers, and how do they work?\n",
            "\n",
            "**The Basics of Transformers**\n",
            "\n",
            "Transformers are based on the encoder-decoder architecture. The encoder converts the input sequence into a fixed-length vector, and the decoder then uses this vector to generate the output sequence.\n",
            "\n",
            "The key innovation in transformers is the self-attention mechanism. This mechanism allows each element in the input sequence to attend to all other elements, regardless of their distance. This is important because it allows transformers to capture long-range dependencies in the data.\n",
            "\n",
            "**Advantages of Transformers**\n",
            "\n",
            "Transformers offer several advantages over traditional neural networks:\n",
            "\n",
            "* **They can handle long-range dependencies.** This is important for NLP tasks such as machine translation and text summarization, where the meaning of a word or phrase can be influenced by words that are far away in the sequence.\n",
            "* **They can parallelize computations.** This is important for training large models on large datasets, as it allows the model to be trained on multiple GPUs simultaneously.\n",
            "* **They are relatively easy to implement.** This makes them a popular choice for researchers and practitioners alike.\n",
            "\n",
            "**Applications of Transformers**\n",
            "\n",
            "Transformers have been used to achieve state-of-the-art results on a wide range of NLP tasks, including:\n",
            "\n",
            "* Machine translation\n",
            "* Text summarization\n",
            "* Question answering\n",
            "* Named entity recognition\n",
            "* Part-of-speech tagging\n",
            "* Language modeling\n",
            "* Speech recognition\n",
            "* Image captioning\n",
            "\n",
            "Transformers are a powerful tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n",
            "\n",
            "**Challenges of Transformers**\n",
            "\n",
            "Despite their advantages, transformers also face some challenges:\n",
            "\n",
            "* **They can be computationally expensive to train.** This is especially true for large models.\n",
            "* **They can be difficult to interpret.** This makes it difficult to understand how they make decisions.\n",
            "* **They can be sensitive to hyperparameters.** This makes it difficult to find the optimal settings for a given task.\n",
            "\n",
            "Despite these challenges, transformers are a promising tool for NLP tasks, and they are likely to continue to be used in a wide variety of applications in the years to come.\n"
          ]
        }
      ]
    }
  ]
}