YouTubeSummary.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount(\"/content/drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "p9CH2h531bVN",
        "outputId": "32c7ae7f-6057-4ea1-e668-a6a7bfff7cee"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import sys\n",
        "sys.path.append(\"/content/drive/MyDrive\")\n",
        "import os\n"
      ],
      "metadata": {
        "id": "-j40rWrZ1kJ0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from constant_keys import *"
      ],
      "metadata": {
        "id": "mOuwEyK52XXZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "os.environ[\"OPENAI_API_KEY\"]= OPENAI_API_KEY"
      ],
      "metadata": {
        "id": "-J0ebZQV1-cX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain\n",
        "!pip install tiktok\n",
        "!pip instlal openai"
      ],
      "metadata": {
        "id": "1tfpFTn01ke7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "4a8d636a-77d5-41a3-b362-31cfdfadf5dd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: langchain in /usr/local/lib/python3.10/dist-packages (0.0.350)\n",
            "Requirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n",
            "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.0.23)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.1)\n",
            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)\n",
            "Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.6.3)\n",
            "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.33)\n",
            "Requirement already satisfied: langchain-community<0.1,>=0.0.2 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.3)\n",
            "Requirement already satisfied: langchain-core<0.2,>=0.1 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.1.0)\n",
            "Requirement already satisfied: langsmith<0.1.0,>=0.0.63 in /usr/local/lib/python3.10/dist-packages (from langchain) (0.0.70)\n",
            "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.23.5)\n",
            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.10.13)\n",
            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.1.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.3)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (3.20.1)\n",
            "Requirement already satisfied: typing-inspect<1,>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from dataclasses-json<0.7,>=0.5.7->langchain) (0.9.0)\n",
            "Requirement already satisfied: jsonpointer>=1.9 in /usr/local/lib/python3.10/dist-packages (from jsonpatch<2.0,>=1.33->langchain) (2.4)\n",
            "Requirement already satisfied: anyio<5,>=3 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1->langchain) (3.7.1)\n",
            "Requirement already satisfied: packaging<24.0,>=23.2 in /usr/local/lib/python3.10/dist-packages (from langchain-core<0.2,>=0.1->langchain) (23.2)\n",
            "Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1->langchain) (4.5.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (2023.11.17)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy<3,>=1.4->langchain) (3.0.1)\n",
            "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain) (1.2.0)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain) (1.0.0)\n",
            "\u001b[31mERROR: Could not find a version that satisfies the requirement tiktok (from versions: none)\u001b[0m\u001b[31m\n",
            "\u001b[0m\u001b[31mERROR: No matching distribution found for tiktok\u001b[0m\u001b[31m\n",
            "\u001b[0mERROR: unknown command \"instlal\" - maybe you meant \"install\"\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install youtube-transcript-api"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pxbkR_yn4L_A",
        "outputId": "56d967fc-4874-4cc4-dde3-1e7b7935b1d9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting youtube-transcript-api\n",
            "  Downloading youtube_transcript_api-0.6.1-py3-none-any.whl (24 kB)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from youtube-transcript-api) (2.31.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->youtube-transcript-api) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->youtube-transcript-api) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->youtube-transcript-api) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->youtube-transcript-api) (2023.11.17)\n",
            "Installing collected packages: youtube-transcript-api\n",
            "Successfully installed youtube-transcript-api-0.6.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.llms import OpenAI\n",
        "from langchain.document_loaders import YoutubeLoader\n"
      ],
      "metadata": {
        "id": "zIFIhI293rcQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "loader = YoutubeLoader.from_youtube_url(\"https://youtu.be/Cv7DXe4QCJA\")"
      ],
      "metadata": {
        "id": "cA7D6ZtL37YT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "docs = loader.load()"
      ],
      "metadata": {
        "id": "b6QY9TB-4Frc"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "docs"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EmSlOW3k4TL3",
        "outputId": "7f173964-288d-436a-b0c9-6f11bbbbe845"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[Document(page_content=\"hi guys welcome back Naji here so in this video we'll be discussing how can we do the segmentation using YOLO okay so here this also very simple thing we can mention task as segment okay task segment and modus sorry not model it's a model as predict and we have a model as YOLO V8 same v8n then this a different model it's a segment okay then here we can mention source as uh source as dog uncore bike uh maybe we can put the source as best do jpj okay I can make sa is equal to True okay let me execute this okay this will will be downloading the model YOLO okay the model is already downloaded and it is saved into run segment and the predict okay it's under run and and segmentor predict so let me open this okay see here we can see the segmentation part so this is The Bu so B bu is like uh it's a kind of a semantic segmentation you can say so bu is in a kind of a green color and we can see the person here the person is um maybe we can see the person is uh in a kind of a maroon color okay so that is how the segmentation works okay now the similar to the predict case or that the classification thing we can also here we can also hide the labels and also we can hide the the score okay so we can add the height count is equal to true and height label is equal to True okay me see this okay so something went wrong okay hide labels is not a valid thing okay okay so I think the spelling is wrong hide labels is true and hide config is equal true okay so it's duplicated method still you can check that so this is saved in run SEC PR two so let me go there here run predict true see uh here the conf uh the score and the uh the labels are labels are not showing here okay so because we set it the height is equal to True okay so that is all about in this video this is a a very short video okay that thank you very much for watching my video please do like and subscribe have a nice day bye-bye\", metadata={'source': 'Cv7DXe4QCJA'})]"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.summarize import load_summarize_chain"
      ],
      "metadata": {
        "id": "BO8pj31Q4TOa"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(temperature=0.7)"
      ],
      "metadata": {
        "id": "9_QGQlWq4mh1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "chain = load_summarize_chain(llm=llm, chain_type=\"stuff\", verbose=True)"
      ],
      "metadata": {
        "id": "e9pOr2u44IS3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "chain.run(docs)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 395
        },
        "id": "_W1sdVvj4rr0",
        "outputId": "1abc3787-fffd-46b7-dc19-7a6167293250"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new StuffDocumentsChain chain...\u001b[0m\n",
            "\n",
            "\n",
            "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mWrite a concise summary of the following:\n",
            "\n",
            "\n",
            "\"hi guys welcome back Naji here so in this video we'll be discussing how can we do the segmentation using YOLO okay so here this also very simple thing we can mention task as segment okay task segment and modus sorry not model it's a model as predict and we have a model as YOLO V8 same v8n then this a different model it's a segment okay then here we can mention source as uh source as dog uncore bike uh maybe we can put the source as best do jpj okay I can make sa is equal to True okay let me execute this okay this will will be downloading the model YOLO okay the model is already downloaded and it is saved into run segment and the predict okay it's under run and and segmentor predict so let me open this okay see here we can see the segmentation part so this is The Bu so B bu is like uh it's a kind of a semantic segmentation you can say so bu is in a kind of a green color and we can see the person here the person is um maybe we can see the person is uh in a kind of a maroon color okay so that is how the segmentation works okay now the similar to the predict case or that the classification thing we can also here we can also hide the labels and also we can hide the the score okay so we can add the height count is equal to true and height label is equal to True okay me see this okay so something went wrong okay hide labels is not a valid thing okay okay so I think the spelling is wrong hide labels is true and hide config is equal true okay so it's duplicated method still you can check that so this is saved in run SEC PR two so let me go there here run predict true see uh here the conf uh the score and the uh the labels are labels are not showing here okay so because we set it the height is equal to True okay so that is all about in this video this is a a very short video okay that thank you very much for watching my video please do like and subscribe have a nice day bye-bye\"\n",
            "\n",
            "\n",
            "CONCISE SUMMARY:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' In this video, Naji discusses how to do segmentation using YOLO. They set a task as segment, source as dog, bike, and best do jpj, and use YOLO V8 model. After downloading the model, they demonstrate a semantic segmentation example and explain how to hide labels and scores. At the end, they thank viewers for watching and ask them to like and subscribe.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "ZRFiMTge4r3N"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}