doc_ingest.ipynb

{"cells":[{"cell_type":"code","source":["# Making sure I'm in the right place on the right branch\n","from google.colab import drive\n","drive.mount('/content/gdrive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"W-uS7QaW2Xoh","executionInfo":{"status":"ok","timestamp":1678815203602,"user_tz":240,"elapsed":18819,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"a4615ab5-8887-4734-a794-6ec5cea1fb52"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/gdrive\n"]}]},{"cell_type":"code","source":["work_dir = \"/content/gdrive/MyDrive/projects/dms/sales_qa/\""],"metadata":{"id":"veDHPSGD2XgA"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["%cd {work_dir}\n","%pwd"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":54},"id":"GgHyuASX2XdB","executionInfo":{"status":"ok","timestamp":1678815203962,"user_tz":240,"elapsed":10,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"ce64f95e-11ac-4496-f3a6-75b6ca15300f"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["/content/gdrive/MyDrive/projects/dms/sales_qa\n"]},{"output_type":"execute_result","data":{"text/plain":["'/content/gdrive/MyDrive/projects/dms/sales_qa'"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":3}]},{"cell_type":"code","source":["!git branch"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UuOVNLuP66wk","executionInfo":{"status":"ok","timestamp":1678280635160,"user_tz":300,"elapsed":1983,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"8e5355b6-2a7e-44d9-e3fb-f8adf0732711"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["* \u001b[32mmain\u001b[m\n"]}]},{"cell_type":"code","source":["%ls -la"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IskET5kB_C4m","executionInfo":{"status":"ok","timestamp":1678280636466,"user_tz":300,"elapsed":238,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"a1381d53-db34-4985-8106-f6bdcb28f10f"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["total 349\n","-rw------- 1 root root  11362 Mar  7 21:23 app.py\n","drwx------ 2 root root   4096 Mar  7 21:23 \u001b[0m\u001b[01;34mdata\u001b[0m/\n","-rw------- 1 root root 323673 Mar  8 13:03 doc_ingest.ipynb\n","drwx------ 9 root root   4096 Mar  7 21:23 \u001b[01;34m.git\u001b[0m/\n","-rw------- 1 root root   1477 Mar  7 21:23 .gitattributes\n","drwx------ 2 root root   4096 Mar  8 10:38 \u001b[01;34mplan_docs\u001b[0m/\n","-rw------- 1 root root    173 Mar  8 11:26 plan_metadata.gsheet\n","-rw------- 1 root root   5379 Mar  8 11:32 plan_metadata.xlsx\n","-rw------- 1 root root    266 Mar  7 21:23 README.md\n","-rw------- 1 root root     86 Mar  7 21:23 requirements.txt\n"]}]},{"cell_type":"markdown","source":["# Create sqllite db with plan info to look up plans"],"metadata":{"id":"ihX3CN9G702g"}},{"cell_type":"code","source":["import pandas as pd\n","plans_df = pd.read_excel(\"plan_metadata.xlsx\")"],"metadata":{"id":"2LH9Monk8FXw"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["plans_df.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":174},"id":"hwuEorYD8FaH","executionInfo":{"status":"ok","timestamp":1678298297064,"user_tz":300,"elapsed":190,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"aa9f004c-7590-417f-d7db-09fed19dfd91"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["   company                     plan_name plan_type  \\\n","0   Humana       Humana Gold Plus (HMO)        HMO   \n","1   Humana       Humana Community (HMO)        HMO   \n","2  Essence       Essence Advantage (HMO)       HMO   \n","3  Essence  Essence Advantage Plus (HMO)       HMO   \n","\n","                                           link_base  \\\n","0  https://www.humana-medicare.com/BenefitSummary...   \n","1  https://www.humana-medicare.com/BenefitSummary...   \n","2  https://shared.portals.lumeris.io/Document/Dow...   \n","3  https://shared.portals.lumeris.io/Document/Dow...   \n","\n","                                 file_name state     county  \n","0                      H5619071000SB23.pdf    KY  Jefferson  \n","1                      H1036236000SB23.pdf    KY  Jefferson  \n","2  2023-EHI-SOBSummaryofBenefitsLOULEX.pdf    KY  Jefferson  \n","3  2023-EHI-SOBSummaryofBenefitsLOULEX.pdf    KY  Jefferson  "],"text/html":["\n","  <div id=\"df-85cf1b5a-1705-410f-81b2-2877f9c57c93\">\n","    <div 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>company</th>\n","      <th>plan_name</th>\n","      <th>plan_type</th>\n","      <th>link_base</th>\n","      <th>file_name</th>\n","      <th>state</th>\n","      <th>county</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Humana</td>\n","      <td>Humana Gold Plus (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://www.humana-medicare.com/BenefitSummary...</td>\n","      <td>H5619071000SB23.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Humana</td>\n","      <td>Humana Community (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://www.humana-medicare.com/BenefitSummary...</td>\n","      <td>H1036236000SB23.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Essence</td>\n","      <td>Essence Advantage (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://shared.portals.lumeris.io/Document/Dow...</td>\n","      <td>2023-EHI-SOBSummaryofBenefitsLOULEX.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>Essence</td>\n","      <td>Essence Advantage Plus (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://shared.portals.lumeris.io/Document/Dow...</td>\n","      <td>2023-EHI-SOBSummaryofBenefitsLOULEX.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-85cf1b5a-1705-410f-81b2-2877f9c57c93')\"\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 0 24 24\"\n","       width=\"24px\">\n","    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n","    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n","  </svg>\n","      </button>\n","      \n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      flex-wrap:wrap;\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","    [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-85cf1b5a-1705-410f-81b2-2877f9c57c93 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-85cf1b5a-1705-410f-81b2-2877f9c57c93');\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","  </div>\n","  "]},"metadata":{},"execution_count":18}]},{"cell_type":"code","source":["from sqlalchemy import create_engine\n","engine = create_engine(f'sqlite:///{work_dir}/plans.sqlite', echo=False)\n","#import sqlite3\n","#cnx = sqlite3.connect()\n","plans_df.to_sql('plans', con=engine)"],"metadata":{"id":"YB0Jy86m8Fct"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["conn = engine.connect()\n","conn.execute('select * from plans').fetchall()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3yE5DujKA59J","executionInfo":{"status":"ok","timestamp":1678281934841,"user_tz":300,"elapsed":211,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"6747a280-0f82-4507-d868-80adbc3f2a52"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["[(0, 'Humana', 'Humana Gold Plus (HMO) ', 'HMO', 'https://www.humana-medicare.com/BenefitSummary/2023PDFs/', 'H5619071000SB23.pdf', 'KY', 'Jefferson'),\n"," (1, 'Humana', 'Humana Community (HMO) ', 'HMO', 'https://www.humana-medicare.com/BenefitSummary/2023PDFs/', 'H1036236000SB23.pdf', 'KY', 'Jefferson'),\n"," (2, 'Essence', 'Essence Advantage (HMO)', 'HMO', 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/', '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf', 'KY', 'Jefferson'),\n"," (3, 'Essence', 'Essence Advantage Plus (HMO)', 'HMO', 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/', '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf', 'KY', 'Jefferson')]"]},"metadata":{},"execution_count":14}]},{"cell_type":"markdown","metadata":{"id":"ZyP3dXRfcXLa"},"source":["# Ingest PDF benefit documents into Chroma vector DB\n","- install and imports\n"]},{"cell_type":"code","source":[],"metadata":{"id":"hDIlKlPR65bK"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"X2R9TjVzNV_E","outputId":"e9468829-9c9a-43bf-b6d3-397109ef86c3","executionInfo":{"status":"ok","timestamp":1678815228547,"user_tz":240,"elapsed":15495,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}}},"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting sentence-transformers\n","  Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.0/86.0 KB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Collecting transformers<5.0.0,>=4.6.0\n","  Downloading transformers-4.26.1-py3-none-any.whl (6.3 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.3/6.3 MB\u001b[0m \u001b[31m55.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (4.65.0)\n","Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (1.13.1+cu116)\n","Requirement already satisfied: torchvision in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (0.14.1+cu116)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (1.22.4)\n","Requirement already satisfied: scikit-learn in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (1.2.2)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (1.10.1)\n","Requirement already satisfied: nltk in /usr/local/lib/python3.9/dist-packages (from sentence-transformers) (3.7)\n","Collecting sentencepiece\n","  Downloading sentencepiece-0.1.97-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m54.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting huggingface-hub>=0.4.0\n","  Downloading huggingface_hub-0.13.2-py3-none-any.whl (199 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.2/199.2 KB\u001b[0m \u001b[31m21.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (6.0)\n","Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (2.25.1)\n","Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (23.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (4.5.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers) (3.9.0)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers) (2022.6.2)\n","Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\n","  Downloading tokenizers-0.13.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.6 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.6/7.6 MB\u001b[0m \u001b[31m66.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: click in /usr/local/lib/python3.9/dist-packages (from nltk->sentence-transformers) (8.1.3)\n","Requirement already satisfied: joblib in /usr/local/lib/python3.9/dist-packages (from nltk->sentence-transformers) (1.1.1)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from scikit-learn->sentence-transformers) (3.1.0)\n","Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.9/dist-packages (from torchvision->sentence-transformers) (8.4.0)\n","Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.9/dist-packages (from requests->huggingface-hub>=0.4.0->sentence-transformers) (4.0.0)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->huggingface-hub>=0.4.0->sentence-transformers) (1.26.15)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->huggingface-hub>=0.4.0->sentence-transformers) (2.10)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->huggingface-hub>=0.4.0->sentence-transformers) (2022.12.7)\n","Building wheels for collected packages: sentence-transformers\n","  Building wheel for sentence-transformers (setup.py) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for sentence-transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125942 sha256=2be7000c5beb0fbf9232fc27c2ecdb55435997bebb19bb107a76f4cb24873691\n","  Stored in directory: /root/.cache/pip/wheels/71/67/06/162a3760c40d74dd40bc855d527008d26341c2b0ecf3e8e11f\n","Successfully built sentence-transformers\n","Installing collected packages: tokenizers, sentencepiece, huggingface-hub, transformers, sentence-transformers\n","Successfully installed huggingface-hub-0.13.2 sentence-transformers-2.2.2 sentencepiece-0.1.97 tokenizers-0.13.2 transformers-4.26.1\n"]}],"source":["!pip install -U sentence-transformers "]},{"cell_type":"code","source":["!pip install langchain"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"T6_80h9LpY0Z","executionInfo":{"status":"ok","timestamp":1678815248699,"user_tz":240,"elapsed":20156,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"f051d6fe-f84b-4f9e-ec61-f99c434ef374"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting langchain\n","  Downloading langchain-0.0.110-py3-none-any.whl (379 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m379.4/379.4 KB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting aiohttp<4.0.0,>=3.8.3\n","  Downloading aiohttp-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m45.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (8.2.2)\n","Collecting dataclasses-json<0.6.0,>=0.5.7\n","  Downloading dataclasses_json-0.5.7-py3-none-any.whl (25 kB)\n","Requirement already satisfied: PyYAML<7,>=6 in /usr/local/lib/python3.9/dist-packages (from langchain) (6.0)\n","Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.22.4)\n","Requirement already satisfied: pydantic<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.10.6)\n","Requirement already satisfied: SQLAlchemy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.4.46)\n","Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.25.1)\n","Collecting async-timeout<5.0,>=4.0.0a3\n","  Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n","Collecting multidict<7.0,>=4.5\n","  Downloading multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 KB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting frozenlist>=1.1.1\n","  Downloading frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (158 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 KB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting aiosignal>=1.1.2\n","  Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n","Collecting yarl<2.0,>=1.0\n","  Downloading yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (264 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 KB\u001b[0m \u001b[31m20.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (22.2.0)\n","Collecting charset-normalizer<4.0,>=2.0\n","  Downloading charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (199 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.2/199.2 KB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting typing-inspect>=0.4.0\n","  Downloading typing_inspect-0.8.0-py3-none-any.whl (8.7 kB)\n","Collecting marshmallow<4.0.0,>=3.3.0\n","  Downloading marshmallow-3.19.0-py3-none-any.whl (49 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.1/49.1 KB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting marshmallow-enum<2.0.0,>=1.5.1\n","  Downloading marshmallow_enum-1.5.1-py2.py3-none-any.whl (4.2 kB)\n","Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic<2,>=1->langchain) (4.5.0)\n","Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (4.0.0)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (1.26.15)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (2022.12.7)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (2.10)\n","Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.9/dist-packages (from SQLAlchemy<2,>=1->langchain) (2.0.2)\n","Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.9/dist-packages (from marshmallow<4.0.0,>=3.3.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (23.0)\n","Collecting mypy-extensions>=0.3.0\n","  Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)\n","Installing collected packages: mypy-extensions, multidict, marshmallow, frozenlist, charset-normalizer, async-timeout, yarl, typing-inspect, marshmallow-enum, aiosignal, dataclasses-json, aiohttp, langchain\n","Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 charset-normalizer-3.1.0 dataclasses-json-0.5.7 frozenlist-1.3.3 langchain-0.0.110 marshmallow-3.19.0 marshmallow-enum-1.5.1 multidict-6.0.4 mypy-extensions-1.0.0 typing-inspect-0.8.0 yarl-1.8.2\n"]}]},{"cell_type":"code","source":["!pip install PyPDF2"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"v-SW53x91M0u","executionInfo":{"status":"ok","timestamp":1678815258322,"user_tz":240,"elapsed":9626,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"5e2fc8cf-976d-4d8f-826c-de0c63e8d324"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting PyPDF2\n","  Downloading pypdf2-3.0.1-py3-none-any.whl (232 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m232.6/232.6 KB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: typing_extensions>=3.10.0.0 in /usr/local/lib/python3.9/dist-packages (from PyPDF2) (4.5.0)\n","Installing collected packages: PyPDF2\n","Successfully installed PyPDF2-3.0.1\n"]}]},{"cell_type":"code","source":["!pip install -U chromadb"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"WfKglAO7l98x","executionInfo":{"status":"ok","timestamp":1678815336042,"user_tz":240,"elapsed":77726,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"f1132dc1-a34e-4647-940a-cfe73d778035"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting chromadb\n","  Downloading chromadb-0.3.11-py3-none-any.whl (41 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.4/41.4 KB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting uvicorn[standard]>=0.18.3\n","  Downloading uvicorn-0.21.0-py3-none-any.whl (57 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.8/57.8 KB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pandas>=1.3 in /usr/local/lib/python3.9/dist-packages (from chromadb) (1.4.4)\n","Collecting duckdb>=0.5.1\n","  Downloading duckdb-0.7.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (15.2 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.2/15.2 MB\u001b[0m \u001b[31m66.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: numpy>=1.21.6 in /usr/local/lib/python3.9/dist-packages (from chromadb) (1.22.4)\n","Collecting fastapi>=0.85.1\n","  Downloading fastapi-0.94.1-py3-none-any.whl (56 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.4/56.4 KB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting clickhouse-connect>=0.5.7\n","  Downloading clickhouse_connect-0.5.15-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (927 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m927.9/927.9 KB\u001b[0m \u001b[31m40.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting requests>=2.28\n","  Downloading requests-2.28.2-py3-none-any.whl (62 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.8/62.8 KB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: sentence-transformers>=2.2.2 in /usr/local/lib/python3.9/dist-packages (from chromadb) (2.2.2)\n","Requirement already satisfied: pydantic>=1.9 in /usr/local/lib/python3.9/dist-packages (from chromadb) (1.10.6)\n","Collecting hnswlib>=0.7\n","  Downloading hnswlib-0.7.0.tar.gz (33 kB)\n","  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","Requirement already satisfied: certifi in /usr/local/lib/python3.9/dist-packages (from clickhouse-connect>=0.5.7->chromadb) (2022.12.7)\n","Requirement already satisfied: urllib3>=1.26 in /usr/local/lib/python3.9/dist-packages (from clickhouse-connect>=0.5.7->chromadb) (1.26.15)\n","Collecting lz4\n","  Downloading lz4-4.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m61.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pytz in /usr/local/lib/python3.9/dist-packages (from clickhouse-connect>=0.5.7->chromadb) (2022.7.1)\n","Collecting zstandard\n","  Downloading zstandard-0.20.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.6 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.6/2.6 MB\u001b[0m \u001b[31m79.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting starlette<0.27.0,>=0.26.1\n","  Downloading starlette-0.26.1-py3-none-any.whl (66 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m66.9/66.9 KB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas>=1.3->chromadb) (2.8.2)\n","Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from pydantic>=1.9->chromadb) (4.5.0)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.28->chromadb) (2.10)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.9/dist-packages (from requests>=2.28->chromadb) (3.1.0)\n","Requirement already satisfied: transformers<5.0.0,>=4.6.0 in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (4.26.1)\n","Requirement already satisfied: torchvision in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (0.14.1+cu116)\n","Requirement already satisfied: scikit-learn in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (1.2.2)\n","Requirement already satisfied: sentencepiece in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (0.1.97)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (1.10.1)\n","Requirement already satisfied: huggingface-hub>=0.4.0 in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (0.13.2)\n","Requirement already satisfied: nltk in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (3.7)\n","Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (1.13.1+cu116)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from sentence-transformers>=2.2.2->chromadb) (4.65.0)\n","Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.9/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (8.1.3)\n","Collecting h11>=0.8\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[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (6.0)\n","Collecting python-dotenv>=0.13\n","  Downloading python_dotenv-1.0.0-py3-none-any.whl (19 kB)\n","Collecting websockets>=10.4\n","  Downloading websockets-10.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (106 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.5/106.5 KB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting httptools>=0.5.0\n","  Downloading httptools-0.5.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (417 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m417.9/417.9 KB\u001b[0m \u001b[31m34.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting uvloop!=0.15.0,!=0.15.1,>=0.14.0\n","  Downloading uvloop-0.17.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.2/4.2 MB\u001b[0m \u001b[31m88.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting watchfiles>=0.13\n","  Downloading watchfiles-0.18.1-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m67.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers>=2.2.2->chromadb) (23.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.4.0->sentence-transformers>=2.2.2->chromadb) (3.9.0)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas>=1.3->chromadb) (1.15.0)\n","Collecting anyio<5,>=3.4.0\n","  Downloading anyio-3.6.2-py3-none-any.whl (80 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m80.6/80.6 KB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers>=2.2.2->chromadb) (0.13.2)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers<5.0.0,>=4.6.0->sentence-transformers>=2.2.2->chromadb) (2022.6.2)\n","Requirement already satisfied: joblib in /usr/local/lib/python3.9/dist-packages (from nltk->sentence-transformers>=2.2.2->chromadb) (1.1.1)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from scikit-learn->sentence-transformers>=2.2.2->chromadb) (3.1.0)\n","Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.9/dist-packages (from torchvision->sentence-transformers>=2.2.2->chromadb) (8.4.0)\n","Collecting sniffio>=1.1\n","  Downloading sniffio-1.3.0-py3-none-any.whl (10 kB)\n","Building wheels for collected packages: hnswlib\n","  Building wheel for hnswlib (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for hnswlib: filename=hnswlib-0.7.0-cp39-cp39-linux_x86_64.whl size=2118475 sha256=fa3350d24aaa9fb533854cc133aeacedb1bf7190e2713d0a52d6a1b09ed0b85b\n","  Stored in directory: /root/.cache/pip/wheels/ba/26/61/fface6c407f56418b3140cd7645917f20ba6b27d4e32b2bd20\n","Successfully built hnswlib\n","Installing collected packages: duckdb, zstandard, websockets, uvloop, sniffio, requests, python-dotenv, lz4, httptools, hnswlib, h11, uvicorn, clickhouse-connect, anyio, watchfiles, starlette, fastapi, chromadb\n","  Attempting uninstall: requests\n","    Found existing installation: requests 2.25.1\n","    Uninstalling requests-2.25.1:\n","      Successfully uninstalled requests-2.25.1\n","Successfully installed anyio-3.6.2 chromadb-0.3.11 clickhouse-connect-0.5.15 duckdb-0.7.1 fastapi-0.94.1 h11-0.14.0 hnswlib-0.7.0 httptools-0.5.0 lz4-4.3.2 python-dotenv-1.0.0 requests-2.28.2 sniffio-1.3.0 starlette-0.26.1 uvicorn-0.21.0 uvloop-0.17.0 watchfiles-0.18.1 websockets-10.4 zstandard-0.20.0\n"]}]},{"cell_type":"code","source":["import pickle\n","import json\n","from sentence_transformers import SentenceTransformer, CrossEncoder, util\n","import gzip\n","import os\n","from torch import load as torch_load\n","from torch import cuda as torch_cuda\n","\n","if not torch_cuda.is_available():\n","    print(\"Warning: No GPU found. Please add GPU to your notebook\")"],"metadata":{"id":"FalS1pl3lZiU","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1678815352162,"user_tz":240,"elapsed":16128,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"4e902e41-1c13-4512-e1b3-d955d49e7a64"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Warning: No GPU found. Please add GPU to your notebook\n"]}]},{"cell_type":"code","source":["from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter"],"metadata":{"id":"YozNQMm_pUvq"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import io\n","from urllib import request\n","from urllib.request import Request, urlopen\n","from PyPDF2 import PdfReader, PdfFileReader\n","import glob"],"metadata":{"id":"_mvxWttK0zKt"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import chromadb\n","from chromadb.config import Settings"],"metadata":{"id":"dgU6DPNxsXMn"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import pandas as pd"],"metadata":{"id":"lPS18ZtssWz3"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["#We use the Bi-Encoder to encode all passages, so that we can use it with sematic search\n","bi_encoder = SentenceTransformer('multi-qa-MiniLM-L6-cos-v1')\n","bi_encoder.max_seq_length = 256     #Truncate long passages to 256 tokens\n","\n","# #The bi-encoder will retrieve 100 documents. We use a cross-encoder, to re-rank the results list to improve the quality\n","# cross_encoder = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')"],"metadata":{"id":"QUPkHJdWm93P","executionInfo":{"status":"ok","timestamp":1678815361875,"user_tz":240,"elapsed":7899,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"colab":{"base_uri":"https://localhost:8080/","height":465,"referenced_widgets":["b138aa06a9304d828d4aa804a63328e9","3163aa05a9fc48759843da21049db5c0","802d51f993b24af0844960285b653700","1886832bbc6e4b958166d932c6d0460e","8d198fa250d84c958b6fcf1b49009bc8","897aad10e1604127a1915f6a8c2939dc","3ce90b9ccda249c2af829f68cd2a669e","4eb5a2f79fc44a7d840346fc389e8f65","5ec59a43860e4b4cb6e86c1bd87bace2","e40239c169cc40dfbf156cdec3e9f6b7","c925f2e1ade241a595c7f1e0b7746fa7","ec44a3ee0fde44d4bae2e7cf96984fb6","23266eca71064796b1114575a257604b","1c01bc9a697044c2bbb42be8796fc4eb","2de9485e0ddb4121b6c2af5d3cd80fa6","7c091484eec042b3b26b550ce307bee3","2651c98cce6648b1bc99f186513a399b","177bc8603ecd43b49546475211c7f868","0c131542642148c9961536ea98c0137c","5071b88ecea54a1ea12a93e6fa68ae40","f5b98acfc7cf42e0ab56ed2dc122ad70","b3541618004b400abed23d873fcf8129","f0a3f17de8464aea8c0858a417954f73","58de80d177a84e4fa3cc24babcb51438","9e83e4e3102b4f80a568a17f4b853926","0830d86cd78a4b1cb385fe888f9e4343","e88b7524a6b649f2b833ab407acd4653","a0e3c6b268d1459987eed3090622b63f","cd73ae34c091463eaf721abaf57f8097","6a8cb3f76eca40b69fb2d4c60fff9644","da41b54262944ff8ab71318d4ae9c939","2285bf4d98d042ff998ca1e9ba468886","bf3db42846e8468892a9b9691cfe2b2a","cc4ea8a17d994dd6afdecb21cfeaabae","4122d5897b0341f286e89526fc4bcf8b","530e0568b08e4446a3a2d7825abe7c4a","bdc82dc3774d4afba63f7cb3a648a4fe","43789605cb504d729e4d0218feb264c5","ba9b0333ca5b4ff38a3d233754557e90","49e93623b6a7482eabaa57aa022dc122","96468298aa014ce7a446a99935300099","92008b6a8dd14d729f4bdde224ee8ba1","f106e897ca324eb1adc3b54c6deaf6c9","57958cc4a57c4cb6b5a06d8ea5fd9a3c","2f5c0d8a7cd94a86ac610d1a202afe91","ff938341c31248a4936a3712b1639365","982d23e0c4e34fe88d725c36c6233490","128edee01303462093110b5fa285e31f","c45c3893cff44b948c10ccf2f579ef07","419be37eac5f426dbb16d9851ba5bc67","105dafda8eaf48c19f07bf4fb81c9ba1","bdd19651227542f3ac1720a681c03257","72ef20a366b34b50846c87c35a115750","1f1324c56a524649ac70dacaf9c8f99d","452a4ef4f5834479b536770f38ea0023","313a969fb7404f7ab03d3e510c5d901d","722ca54383bd45c698c92725622cc5a9","57ed3b1684044e40a87856254c2209b6","572ebca45077443aac1ad00b16445aee","fc2711786fbf46cd86b40356b174edb7","3b6af6f90b0d4f4899d6736e9970e845","331623885aab458db43c5b8523f11e1b","76234ada88a14a39815261ae69df8b58","cac81ef5f6494672a685e887f710bd3b","ae4c84c9644044458deabb8cc44b1484","766538d72846478ea077c99b90227e67","19c051868b08475dbe5f3b0dd6d6e060","811f85a540624291a4447c8486d0689e","2ab11e53a1ef4cad8bc715323a27e564","7d46fda7ba5447dda9c20923c99316b3","463bbd9f8f314654a2c04158199e0d3a","59902eb789434a33afdfb95010ba94c2","351cc2ed2c1c401c894079892c66385e","b0dce9de32ee4764961b34f186fed478","0e60bd79772743f380804c5062751e5c","962edf0e1af54ab6b4cd4a0657293721","53f252e74ac447e4bc26f1fdaed9b115","ca5074be81cb47b1941dad04caf87c65","f952d97cfda94aa9bb86f6cb7ef36aa2","11b0350ded3b46bc9f1165dcea2e5d45","5e6be0a4986d49eabf2af04209f41199","bf6e6b27866b436ebaf88e5708e286ab","39eb5c90bd684c44920af2bf9aa09717","0b8be20124e74782927c0e5153790c0b","a5e84329dbc7483cb06990cab5ef0f1b","54e2256e878d4066971e659826c6da60","1ba572ad1fb9452a96c0f30e9d981334","ccd05565f8284fb2b4f82123f6132544","afffdf68830840feb2ab6fd307f71494","4bab0d0fe5554221b5bd35e4dfd6c290","ba551fb0cd49461e8f13b67612f65993","f140e4b6fc48424aac34fc009d4374a4","d6966de0903e47788a8c3dd422a1df1c","80bdf38dbcae4e03a7b1fde210933a52","50309917f4884787a5ff8eeae893a1b4","055048a8b16e42f69baad57e438f9c5e","00defac0a3844677a439823caeaeb5cb","14029eaf55a44a1a863764b815c2b07b","043a7d73810f47cbab03e89c93cfaa91","32528eb2f60d40cb8e5fc74ba976345e","593a1d80de49408d81f776c1d2c7faea","891f1b01646b49c48bd05053df1fef16","43e174cff8f64c4783a9f1e3a5391201","54f01a1ab4e8400fa73c59b8603a4378","a461847f45cb4fb7bf398c6ed7dd910f","bdce7da8e16b4c8d9579232a9360c1a6","6f3c94d707a048e2b56b753e2cff884a","d4106d077a1d4a36b14e3b28e8b2a19c","73e35bb344ab4e96b48e614b9d791047","6a0602071c3c44cdbbc8ba9496ef7dba","a53a60056c87417eba56660294b39ba7","ac27b3a70e9c46ffa5fee81159632b60","abb28254a1b4446c8181364892da547d","45989b5303c243978757bb64cbbfb24c","402924ab2cdf4152bb2b0e2e07373c03","aa1c9838fbf846f991a8c8b4aac6ad73","772746054aff45c9bb2e11af14249cff","a5a07686ee9c466586d0053bb178ebc4","382cbe2fcb3c4a27bc5347cf15c7d2fc","6b63577927ac45008f4bbd51ac6f75d0","dd2168b61f0a4af286cc4d0c0c6f3a44","93fc525e43d64f35b5278cfbdffa8b3e","9871d3b3b2414179b0a979fbadc1d3ee","8e85290f8d6a420591e5655c638c31e4","785acd5dd38f481483afe92c1ddcd496","bfece0017b914c96bdafccf921d6ab8b","2122594f781a4cefa903bc8b5c826b77","dcfe5fa3b505427f96273b24c35618fd","cdcd9f35d5af4b7992266f5f12e6a66f","c38c65f297ff4b2a9d864e10049de670","ac17747a2f1e40ca8f8a724280fde72a","b090df0e82b144f680f9758300bf475b","55c89cb46a744f909da5cfffe254bbc3","1bc885119d374107896e65f34e9195fb","7639eab1ff5a4fd08ef2fea77af624b0","90d3330947a24f5f87e7f001c45e563c","ed876d27136d45859c7a2f250f714f89","1aa841d3489b4a0aad8d03af1db9d431","d86c8b087abd4c4a8f0025bb62a2d968","b71a8d721ad947278ea9eb50640ed642","8c98e217657e4424bb80bb1bec27815f","58aa5e0dbd774c9ca49c876b3335d405","2ff08d3beb1444c9977a6bde470e40ac","a0dd1a2336ac499f8059a920d29ff8f2","e7e356b52dee40d58422e10b7fadcdce","7d05d2d945e44c6097c90ddb60135497","280811af738848469324c8f6fa5ba349","f441ae1f11c74ab7bde13204b4f94ab4","9e5c0e875f1c4df49e076600aa07c27d","d52138057e8c4689a370439000244b25","b180984828aa4418b8a6fc3b6f238ff1","22b8df67284e489ab06dea21de80ba07","f102594506c0474590147761fbd7ece4","8a5c19af1c854d4ab27f20fec023bc35"]},"outputId":"9b479119-fcb6-431c-a793-4c434d3d6e86"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["Downloading (…)5fedf/.gitattributes:   0%|          | 0.00/737 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"b138aa06a9304d828d4aa804a63328e9"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)_Pooling/config.json:   0%|          | 0.00/190 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"ec44a3ee0fde44d4bae2e7cf96984fb6"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)2cb455fedf/README.md:   0%|          | 0.00/11.5k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"f0a3f17de8464aea8c0858a417954f73"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)b455fedf/config.json:   0%|          | 0.00/612 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"cc4ea8a17d994dd6afdecb21cfeaabae"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)ce_transformers.json:   0%|          | 0.00/116 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"2f5c0d8a7cd94a86ac610d1a202afe91"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)edf/data_config.json:   0%|          | 0.00/25.5k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"313a969fb7404f7ab03d3e510c5d901d"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading pytorch_model.bin:   0%|          | 0.00/90.9M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"19c051868b08475dbe5f3b0dd6d6e060"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)nce_bert_config.json:   0%|          | 0.00/53.0 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"ca5074be81cb47b1941dad04caf87c65"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)cial_tokens_map.json:   0%|          | 0.00/112 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"afffdf68830840feb2ab6fd307f71494"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)5fedf/tokenizer.json:   0%|          | 0.00/466k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"32528eb2f60d40cb8e5fc74ba976345e"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)okenizer_config.json:   0%|          | 0.00/383 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"a53a60056c87417eba56660294b39ba7"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)fedf/train_script.py:   0%|          | 0.00/13.8k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"93fc525e43d64f35b5278cfbdffa8b3e"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)2cb455fedf/vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"55c89cb46a744f909da5cfffe254bbc3"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)455fedf/modules.json:   0%|          | 0.00/349 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"a0dd1a2336ac499f8059a920d29ff8f2"}},"metadata":{}}]},{"cell_type":"markdown","source":["# ingest pdf from URL"],"metadata":{"id":"SdnsRpSA2P0m"}},{"cell_type":"code","source":["!ls './plan_docs/Humana/'"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"pJrCqHJK2CFq","executionInfo":{"status":"ok","timestamp":1678306169425,"user_tz":300,"elapsed":544,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"31775c3d-78f3-4223-ce13-8022da1a9d1d"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["H1036236000SB23.pdf  H5619071000SB23.pdf\n"]}]},{"cell_type":"code","source":["!ls './plan_docs/Essence/'"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ehayr6n7gCsv","executionInfo":{"status":"ok","timestamp":1678306169426,"user_tz":300,"elapsed":25,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"d466f181-76b6-49aa-f2f9-dcd0ad5fa59e"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["2023-EHI-SOBSummaryofBenefitsLOULEX.pdf\n"]}]},{"cell_type":"code","source":["text_splitter = CharacterTextSplitter(chunk_size=200, chunk_overlap=0,  separator='\\n' )"],"metadata":{"id":"TmtS7nyuYRGN"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["plans_df.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":174},"id":"0Vu4IfoTgqXl","executionInfo":{"status":"ok","timestamp":1678306169426,"user_tz":300,"elapsed":16,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"c818192b-3293-4aac-b5d5-f5febc9b8f52"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["   company                     plan_name plan_type  \\\n","0   Humana       Humana Gold Plus (HMO)        HMO   \n","1   Humana       Humana Community (HMO)        HMO   \n","2  Essence       Essence Advantage (HMO)       HMO   \n","3  Essence  Essence Advantage Plus (HMO)       HMO   \n","\n","                                           link_base  \\\n","0  https://www.humana-medicare.com/BenefitSummary...   \n","1  https://www.humana-medicare.com/BenefitSummary...   \n","2  https://shared.portals.lumeris.io/Document/Dow...   \n","3  https://shared.portals.lumeris.io/Document/Dow...   \n","\n","                                 file_name state     county  \n","0                      H5619071000SB23.pdf    KY  Jefferson  \n","1                      H1036236000SB23.pdf    KY  Jefferson  \n","2  2023-EHI-SOBSummaryofBenefitsLOULEX.pdf    KY  Jefferson  \n","3  2023-EHI-SOBSummaryofBenefitsLOULEX.pdf    KY  Jefferson  "],"text/html":["\n","  <div id=\"df-e6ed0672-87f4-4424-bd73-791bda2ca40c\">\n","    <div 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>company</th>\n","      <th>plan_name</th>\n","      <th>plan_type</th>\n","      <th>link_base</th>\n","      <th>file_name</th>\n","      <th>state</th>\n","      <th>county</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>Humana</td>\n","      <td>Humana Gold Plus (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://www.humana-medicare.com/BenefitSummary...</td>\n","      <td>H5619071000SB23.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Humana</td>\n","      <td>Humana Community (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://www.humana-medicare.com/BenefitSummary...</td>\n","      <td>H1036236000SB23.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Essence</td>\n","      <td>Essence Advantage (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://shared.portals.lumeris.io/Document/Dow...</td>\n","      <td>2023-EHI-SOBSummaryofBenefitsLOULEX.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>Essence</td>\n","      <td>Essence Advantage Plus (HMO)</td>\n","      <td>HMO</td>\n","      <td>https://shared.portals.lumeris.io/Document/Dow...</td>\n","      <td>2023-EHI-SOBSummaryofBenefitsLOULEX.pdf</td>\n","      <td>KY</td>\n","      <td>Jefferson</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e6ed0672-87f4-4424-bd73-791bda2ca40c')\"\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 0 24 24\"\n","       width=\"24px\">\n","    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n","    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n","  </svg>\n","      </button>\n","      \n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      flex-wrap:wrap;\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","    [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-e6ed0672-87f4-4424-bd73-791bda2ca40c 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-e6ed0672-87f4-4424-bd73-791bda2ca40c');\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","  </div>\n","  "]},"metadata":{},"execution_count":18}]},{"cell_type":"code","source":["prefx = plans_df[plans_df.file_name=='2023-EHI-SOBSummaryofBenefitsLOULEX.pdf'].link_base.values[0]\n","prefx"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":36},"id":"xJ3LGhNcgOxl","executionInfo":{"status":"ok","timestamp":1678306169427,"user_tz":300,"elapsed":15,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"5144b149-7a57-4217-dc11-f4ae9cdcba71"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/'"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":19}]},{"cell_type":"code","source":["dir = './plan_docs'\n","for root, dirs, files in os.walk(dir):\n","  for rootdir in dirs:\n","    print(dir)\n","  for filename in files:\n","    print(os.path.join(root, filename))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"zSjYssRIh7y2","executionInfo":{"status":"ok","timestamp":1678306169427,"user_tz":300,"elapsed":14,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"ea7dd965-9645-454a-c367-389063efbfcf"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["./plan_docs\n","./plan_docs\n","./plan_docs/Humana/H5619071000SB23.pdf\n","./plan_docs/Humana/H1036236000SB23.pdf\n","./plan_docs/Essence/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf\n"]}]},{"cell_type":"code","source":["# iterate over files in\n","# that directory\n","dir = './plan_docs'\n","\n","for plan in os.listdir(dir):\n","    d = os.path.join(dir, plan)\n","    # checking if it is a file\n","    if os.path.isdir(d):\n","        print(\"Creating texts for:\", plan)\n","        print(\"Files in:\",d)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Ed-_3uOijdIq","executionInfo":{"status":"ok","timestamp":1678306169427,"user_tz":300,"elapsed":10,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"73ebd1bd-72f7-4b70-ac23-3a6c7b574308"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Creating texts for: Humana\n","Files in: ./plan_docs/Humana\n","Creating texts for: Essence\n","Files in: ./plan_docs/Essence\n"]}]},{"cell_type":"code","source":["import glob\n","import os\n","\n","dir = './plan_docs'\n","\n","mypassages = []\n","mymetadatas = []\n","\n","for plan in os.listdir(dir):\n","  d = os.path.join(dir, plan)\n","  # checking if it is a file\n","  if os.path.isdir(d):\n","    print(\"Creating texts for:\", plan)\n","    print(\"Files in:\",d)\n","\n","    for pth in glob.glob(f'{d}/*.pdf'):\n","      fl_pth, fl_nm = os.path.split(pth)\n","      print(fl_nm)\n","\n","      prefx = plans_df[plans_df.file_name==fl_nm]\n","      if len(prefx)>0:\n","        prefx = prefx.link_base.values[0]\n","      else:\n","        continue # If there are no records matching that file, then skip\n","      print(prefx)\n","\n","      with open(pth, 'rb') as f:\n","        pdf_file = PdfReader(f)\n","        for pg, p_obj in enumerate(pdf_file.pages):\n","        #  print(pg+1)\n","          p_txt = p_obj.extract_text()\n","          #passages = p_txt.split('\\n')\n","          texts = text_splitter.split_text(p_txt)\n","          for t in texts:\n","            mypassages.append(t)\n","            d = {'doc_type':'plan benefits', 'company':plan.lower(), 'source':fl_nm, 'page': pg+1, 'url':prefx+str(fl_nm)+'#page='+str(pg+1)}\n","            mymetadatas.append(d)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"a-NpNqGWh71a","executionInfo":{"status":"ok","timestamp":1678306253414,"user_tz":300,"elapsed":6972,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"479fe6cf-1a40-4d66-837f-3598db8bc753"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Creating texts for: Humana\n","Files in: ./plan_docs/Humana\n","H5619071000SB23.pdf\n","https://www.humana-medicare.com/BenefitSummary/2023PDFs/\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]},{"output_type":"stream","name":"stdout","text":["H1036236000SB23.pdf\n","https://www.humana-medicare.com/BenefitSummary/2023PDFs/\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]},{"output_type":"stream","name":"stdout","text":["Creating texts for: Essence\n","Files in: ./plan_docs/Essence\n","2023-EHI-SOBSummaryofBenefitsLOULEX.pdf\n","https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 243, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 299, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 417, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 288, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 540, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 211, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 291, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 201, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 570, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 303, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 305, which is longer than the specified 200\n"]}]},{"cell_type":"code","source":["import glob\n","import os\n","\n","dir = './other_docs'\n","\n","meta_dict = {'10050-Medicare-and-You.pdf':{'prefix':'https://www.medicare.gov/publications/',\n","                                           'doc_type':'general medicare info', 'company':'CMS'}\n","}\n","\n","mypassages = []\n","mymetadatas = []\n","\n","\n","for pth in glob.glob(f'{dir}/*.pdf'):\n","  fl_pth, fl_nm = os.path.split(pth)\n","  print(fl_nm)\n","\n","  prefx = meta_dict[fl_nm]['prefix']\n","  print(prefx)\n","\n","  with open(pth, 'rb') as f:\n","    pdf_file = PdfReader(f)\n","    for pg, p_obj in enumerate(pdf_file.pages):\n","    #  print(pg+1)\n","      p_txt = p_obj.extract_text()\n","      #passages = p_txt.split('\\n')\n","      texts = text_splitter.split_text(p_txt)\n","      for t in texts:\n","        mypassages.append(t)\n","        d = {'doc_type':meta_dict[fl_nm]['doc_type'], 'company':meta_dict[fl_nm]['company'], 'source':fl_nm, 'page': pg+1, 'url':prefx+str(fl_nm)+'#page='+str(pg+1)}\n","        mymetadatas.append(d)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1678815403738,"user_tz":240,"elapsed":9587,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"e4a8c8e8-7148-4d44-ff4c-1981a2779188","id":"grDtG31bJrSs"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["10050-Medicare-and-You.pdf\n","https://www.medicare.gov/publications/\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 240, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 310, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 220, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 274, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 213, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 254, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 244, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 227, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 370, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 203, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 278, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 406, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 285, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 271, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 210, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 234, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 218, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 203, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 208, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 346, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 257, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 262, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 338, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 212, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 428, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 411, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 364, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 283, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 216, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 605, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 328, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 204, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 301, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 261, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 224, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 411, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 404, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 256, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 258, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 296, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 207, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 241, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 288, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 454, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 304, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 317, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 282, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 272, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 231, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 315, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 306, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 392, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 285, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 221, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 372, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 301, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 556, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 327, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 560, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 393, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 285, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 240, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 314, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 420, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 430, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 230, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 222, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 451, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 246, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 383, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 447, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 273, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 361, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 482, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 406, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 218, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 222, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 218, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 315, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 251, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 203, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 212, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 286, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 208, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 233, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 235, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 445, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 455, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 390, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 211, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 213, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 215, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 631, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 352, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 298, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 426, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 202, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 360, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 307, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 232, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 214, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 386, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 231, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 410, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 795, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 376, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 373, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 412, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 222, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 454, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 387, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 371, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 496, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 280, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 577, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 403, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 215, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 380, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 490, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 349, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 583, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 283, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 433, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 323, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 238, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 308, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 229, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 249, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 294, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 285, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 421, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 212, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 238, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 550, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 251, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 326, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 415, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 297, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 539, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 254, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 236, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 418, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 299, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 273, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 448, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 213, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 230, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 358, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 464, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 313, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 215, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 460, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 214, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 224, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 435, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 266, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 334, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 343, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 261, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 424, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 264, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 620, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 510, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 287, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 223, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 378, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 221, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 304, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 593, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 295, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 246, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 280, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 406, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 354, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 236, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 479, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 282, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 296, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 204, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 263, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 364, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 346, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 446, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 259, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 298, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 371, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 256, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 482, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 207, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 317, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 245, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 374, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 332, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 207, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 208, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 345, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 230, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 220, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 297, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 213, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 737, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 300, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 544, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 374, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 202, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 219, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 423, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 225, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 346, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 204, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 248, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 288, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 304, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 232, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 369, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 209, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 227, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 300, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 351, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 216, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 314, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 292, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 297, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 236, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 358, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 440, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 220, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 296, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 299, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 583, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 529, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 206, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 346, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 365, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 334, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 236, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 298, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 307, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 406, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 288, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 313, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 300, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 912, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 374, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 385, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 209, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 263, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 313, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 530, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 414, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 219, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 266, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 247, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 227, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 448, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 222, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 371, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 360, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 369, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 281, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 934, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 297, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 212, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 389, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 212, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 303, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 278, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 225, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 249, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 697, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 358, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 276, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 282, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 217, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 296, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 335, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 533, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 332, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 240, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 355, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 207, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 277, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 359, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 226, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 336, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 257, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 746, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 232, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 369, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 406, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 274, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 246, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 446, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 479, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 236, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 393, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 317, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 441, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 390, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 271, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 206, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 301, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 231, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 281, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 239, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 332, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 237, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 214, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 276, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 349, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 349, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 237, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 266, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 408, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 218, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 358, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 233, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 404, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 201, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 205, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 206, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 395, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 227, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 597, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 312, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 270, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 251, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 294, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 293, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 344, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 526, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 335, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 334, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 322, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 335, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 395, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 363, which is longer than the specified 200\n","WARNING:root:Created a chunk of size 201, which is longer than the specified 200\n"]}]},{"cell_type":"code","source":["mypassages[0]"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":36},"id":"fIpaS98ah732","executionInfo":{"status":"ok","timestamp":1678815412512,"user_tz":240,"elapsed":113,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"c5f564de-d183-4c74-ccd2-ec581a1bb8ae"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["'2023Medicare\\n& YouThe official U.S. government \\nMedicare handbook'"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":18}]},{"cell_type":"code","source":["prefx = 'https://www.humana-medicare.com/BenefitSummary/2023PDFs/'"],"metadata":{"id":"YYsvFS8OidMO"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["mypassages = []\n","mymetadatas = []\n","for pth in glob.glob('./ama_wiki/data/bene_pdf/*.pdf'):\n","  fl_pth, fl_nm = os.path.split(pth)\n","  print(fl_nm)\n","  with open(pth, 'rb') as f:\n","    pdf_file = PdfReader(f)\n","    for pg, p_obj in enumerate(pdf_file.pages):\n","    #  print(pg+1)\n","      p_txt = p_obj.extract_text()\n","      #passages = p_txt.split('\\n')\n","      texts = text_splitter.split_text(p_txt)\n","      for t in texts:\n","        mypassages.append(t)\n","        d = {'source':fl_nm, 'page': pg+1, 'url':prefx+str(fl_nm)+'#page='+str(pg+1)}\n","        mymetadatas.append(d)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"jwkVTN9Cg0Mm","executionInfo":{"status":"ok","timestamp":1677874033906,"user_tz":300,"elapsed":12818,"user":{"displayName":"Greg Hayworth","userId":"07798746719312628238"}},"outputId":"8a8f9158-f240-4d86-81ce-c7e48fb38feb"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["H5619075000SB23.pdf\n","S5884138000SB23.pdf\n","H1036234000SB23.pdf\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]},{"output_type":"stream","name":"stdout","text":["H1036235000SB23.pdf\n","H5216324000SB23.pdf\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]},{"output_type":"stream","name":"stdout","text":["H5216107000SB23.pdf\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]},{"output_type":"stream","name":"stdout","text":["H1036236000SB23.pdf\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:root:Created a chunk of size 329, which is longer than the specified 200\n"]}]},{"cell_type":"code","source":["myembeddings = bi_encoder.encode(mypassages, convert_to_tensor=True, show_progress_bar=True).tolist()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":49,"referenced_widgets":["5d41e7c4c7cf4eff932b0b7d245003bb","b191e73abc0e4064b146e6b143c27c7f","d232c51e5ff04332abce4e4029616089","812e7ce0577c48ae8d7dc55f35da6a2f","ab0c84ed814548a792a4b8295986ae27","908102cf75904ef68efcd27498b6bd5f","6214ec5f027c4fee8651fdcfa64a3c59","04ec9d98e8c14c97ab8453b5cb7b196f","a6c905aa92614362bff4a874fcb214f8","f7a195fe58934cb487daf4053b97c266","3be5dfec2f674e48ad23cf43624dfd44"]},"id":"UcqhxylOkOup","executionInfo":{"status":"ok","timestamp":1678815495203,"user_tz":240,"elapsed":66377,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"f7f04ac6-d316-46af-c28a-563d3a9ce16e"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["Batches:   0%|          | 0/49 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"5d41e7c4c7cf4eff932b0b7d245003bb"}},"metadata":{}}]},{"cell_type":"code","source":["myembeddings[0][:10]"],"metadata":{"id":"ETDTU0YskOkd","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1678815497801,"user_tz":240,"elapsed":116,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"e284379a-58fa-4a09-d250-ac8429ec58f4"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["[-0.054114993661642075,\n"," 0.0700472816824913,\n"," -0.09043540805578232,\n"," -0.08235538750886917,\n"," 0.005439667031168938,\n"," 0.07311709970235825,\n"," -0.019055908545851707,\n"," 0.0453181192278862,\n"," -0.11824097484350204,\n"," 0.07970310002565384]"]},"metadata":{},"execution_count":20}]},{"cell_type":"code","source":["chroma_client = chromadb.Client(settings=Settings(\n","    chroma_db_impl=\"duckdb+parquet\",\n","    persist_directory=\"./data/mychromadb/\" # Optional, defaults to .chromadb/ in the current directory\n","))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ltMoTm1vkOM6","executionInfo":{"status":"ok","timestamp":1678815511374,"user_tz":240,"elapsed":2229,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"dfd7f288-d581-4f01-bb1a-0b7de17cf085"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["DEBUG:Chroma:Logger created\n"]},{"output_type":"stream","name":"stdout","text":["Running Chroma using direct local API.\n","loaded in 1959 embeddings\n","loaded in 2 collections\n"]}]},{"cell_type":"code","source":["!ls './data/mychromadb/'"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"W8c2EQlc2Oc0","executionInfo":{"status":"ok","timestamp":1678289309499,"user_tz":300,"elapsed":1034,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"bca51ee2-c6be-4205-86c3-2f26f49029a4"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["chroma-collections.parquet  chroma-embeddings.parquet  index\n"]}]},{"cell_type":"code","source":["#chroma_client.delete_collection(name=\"essence\")"],"metadata":{"id":"UkP3SvYN2OWE"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["collection = chroma_client.create_collection(name=\"faq_collection\", embedding_function=bi_encoder)"],"metadata":{"id":"N33r1sDe2OQD"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["mx_id = (collection.count() - 1)\n","mx_id"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"eF0pekWTtWD_","executionInfo":{"status":"ok","timestamp":1678815520163,"user_tz":240,"elapsed":120,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"12977915-59d3-4877-aa32-1139454bbc62"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["-1"]},"metadata":{},"execution_count":23}]},{"cell_type":"code","source":["# start from max of current value doc id\n","mydocids = []\n","for i, p in enumerate(mypassages):\n","  mydocids.append(str(i) ) #+(mx_id+1) ### for subsequent runs\n","len(mydocids)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GEHaf0itjr_m","executionInfo":{"status":"ok","timestamp":1678815525649,"user_tz":240,"elapsed":157,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"5e008fa6-0a72-4c12-a0a4-d6c6b6727bf0"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["1556"]},"metadata":{},"execution_count":24}]},{"cell_type":"code","source":["collection.add(\n","    embeddings= myembeddings,\n","    documents= mypassages,\n","    metadatas=mymetadatas,\n","    ids=mydocids\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Rs6OBCvG2OKH","executionInfo":{"status":"ok","timestamp":1678815537683,"user_tz":240,"elapsed":1697,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"fb9b6758-58fb-4434-cb1d-49afb2be60c3"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["DEBUG:Chroma:Index not found\n","DEBUG:Chroma:Index saved to ./data/mychromadb//index/index.bin\n","DEBUG:Chroma:Index saved to ./data/mychromadb//index/index.bin\n"]}]},{"cell_type":"code","source":["collection.get(ids=[str(567)],\n","               include=[\"documents\",\"metadatas\"])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"BkzqWk6wtje3","executionInfo":{"status":"ok","timestamp":1678815540047,"user_tz":240,"elapsed":129,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"69500664-37c0-469e-ab0e-63909f8abdc2"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'ids': ['567'],\n"," 'embeddings': None,\n"," 'documents': ['Preventive service  \\nLung cancer screenings \\nMedicare covers lung cancer screenings with low dose computed tomography \\nonce per year if you meet these updated conditions: \\n• You’re 50–77.'],\n"," 'metadatas': [{'doc_type': 'general medicare info',\n","   'company': 'CMS',\n","   'source': '10050-Medicare-and-You.pdf',\n","   'page': 45,\n","   'url': 'https://www.medicare.gov/publications/10050-Medicare-and-You.pdf#page=45'}]}"]},"metadata":{},"execution_count":26}]},{"cell_type":"code","source":["# important to do this if you want to save the data for re-use\n","chroma_client.persist()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"-XpFU35Zssa2","executionInfo":{"status":"ok","timestamp":1678815555925,"user_tz":240,"elapsed":1135,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"62678518-b6c8-4758-ed62-7d8e6893ca45"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Persisting DB to disk, putting it in the save folder ./data/mychromadb/\n"]},{"output_type":"execute_result","data":{"text/plain":["True"]},"metadata":{},"execution_count":27}]},{"cell_type":"code","source":["!ls './data/mychromadb/'"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"O8w01y9vGMLt","executionInfo":{"status":"ok","timestamp":1678306702435,"user_tz":300,"elapsed":264,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"f4c059da-7727-495a-90b8-b60c18115760"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["chroma-collections.parquet  chroma-embeddings.parquet  index\n"]}]},{"cell_type":"markdown","source":["# Use existing collection"],"metadata":{"id":"sg331hx1tZbR"}},{"cell_type":"code","source":["chroma_client2 = chromadb.Client(settings=Settings(\n","    chroma_db_impl=\"duckdb+parquet\",\n","    persist_directory=\"./data/mychromadb/\" # Optional, defaults to .chromadb/ in the current directory\n","))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0Rs_e9kevzsN","executionInfo":{"status":"ok","timestamp":1678306704826,"user_tz":300,"elapsed":225,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"d67afffd-84bf-444b-f22d-0030a49fcc50"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Running Chroma using direct local API.\n","loaded in 1959 embeddings\n","loaded in 2 collections\n"]}]},{"cell_type":"code","source":["collection = chroma_client2.get_collection(name=\"plan_collection\", embedding_function=bi_encoder)"],"metadata":{"id":"ipvck4yltY4X"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"hm93bQActYJE"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["company = 'humana'\n","results = collection.query(\n","    #query_texts=['prostate cancer screening'],\n","    query_embeddings = [bi_encoder.encode('prostate cancer screening')],\n","    include=[\"documents\",\"metadatas\", \"embeddings\"],\n","    where={\"company\": company},\n","    n_results=3)\n","for d in results.get('documents')[0]:\n","  print(d)\n","  print('\\n')\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"VcJtkk-72OEG","executionInfo":{"status":"ok","timestamp":1678306874288,"user_tz":300,"elapsed":316,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"03390fab-997b-465f-89c4-953981978f5e"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["DEBUG:Chroma:time to pre process our knn query: 0.0002930164337158203\n","DEBUG:Chroma:time to run knn query: 0.00012946128845214844\n"]},{"output_type":"stream","name":"stdout","text":["•Diabetes screenings \n","•HIV screening \n","•Medical nutrition therapy services \n","•Obesity screening and counseling \n","•Prostate cancer screenings (PSA)\n","\n","\n","•Diabetes screenings \n","•HIV screening \n","•Medical nutrition therapy services \n","•Obesity screening and counseling \n","•Prostate cancer screenings (PSA)\n","\n","\n","•Cardiovascular screenings \n","•Cervical and vaginal cancer screening \n","•Colorectal cancer screenings (colonoscopy, fecal occult blood test, \n","flexible sigmoidoscopy) \n","•Depression screening\n","\n","\n"]}]},{"cell_type":"code","source":["def rtrv(qry,top_k=20):\n","  results = collection.query(\n","    query_embeddings=[ bi_encoder.encode(qry) ],\n","    n_results=top_k,\n","    )\n","  return results"],"metadata":{"id":"mdiMLPGYwaLA"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def vdb_where(qry,where,top_k=20):\n","  results = collection.query(\n","    query_embeddings=[ bi_encoder.encode(qry) ],\n","    n_results=top_k,\n","    where=where,\n","    )\n","  return results"],"metadata":{"id":"PrB37vXt8j5t"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def vdb_qry(qry,company,top_n=5):\n","  results = collection.query(\n","    query_embeddings=[ bi_encoder.encode(qry) ],\n","    n_results=top_n,\n","    where={\"company\": company},\n","    include=['documents', 'metadatas', 'distances', 'embeddings']\n","    )\n","  #return results\n","  rslt_pd = pd.DataFrame(results ).explode(['ids','documents', 'metadatas', 'distances', 'embeddings'])\n","  rslt_fmt = pd.concat([rslt_pd.drop(['metadatas'], axis=1), rslt_pd['metadatas'].apply(pd.Series)], axis=1 )\n","  return rslt_fmt"],"metadata":{"id":"DgB59Bz_2NwW"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["qry = 'is prostate cancer screening covered?'\n","src = 'H1036236000SB23.pdf'\n","company = 'essence'\n","where={'company':company,}# 'source':src}\n","rslt = vdb_where(qry, where=where, top_k=5)\n","rslt"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"06jN7B9arW2f","executionInfo":{"status":"ok","timestamp":1678309521395,"user_tz":300,"elapsed":242,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"d80cacd9-65cb-4313-e1e0-ef99e500db79"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["DEBUG:Chroma:time to pre process our knn query: 0.0001361370086669922\n","DEBUG:Chroma:time to run knn query: 0.0002200603485107422\n"]},{"output_type":"execute_result","data":{"text/plain":["{'ids': [['433', '437', '429', '430', '485']],\n"," 'embeddings': None,\n"," 'documents': [['• Obesity screening and therapy to promote sustained weight loss \\n• Prostate cancer screening exams \\n• Screening and counseling to reduce alcohol misuse',\n","   '• Screening for lung cancer with low-dose computed tomography (LDCT) \\n• Screening for sexually transmitted infections (STIs) and counseling to prevent STIs',\n","   'You pay nothing. Our plans cover many preventive services, including: \\n• Abdominal aortic aneurysm screening \\n• Annual wellness visit \\n• Bone mass measurement \\n• Breast cancer screening (mammogram)',\n","   '• Cardiovascular disease risk reduction visit (therapy for cardiovascular disease) \\n• Cardiovascular disease testing \\n• Cervical and vaginal cancer screening \\n• Colorectal cancer screening',\n","   'Insulins, including full cost-sharing information. The program doesn’t apply during the catastrophic coverage stage or if you receive Extra Help.']],\n"," 'metadatas': [[{'doc_type': 'plan benefits',\n","    'company': 'essence',\n","    'source': '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf',\n","    'page': 6,\n","    'url': 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf#page=6'},\n","   {'doc_type': 'plan benefits',\n","    'company': 'essence',\n","    'source': '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf',\n","    'page': 7,\n","    'url': 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf#page=7'},\n","   {'doc_type': 'plan benefits',\n","    'company': 'essence',\n","    'source': '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf',\n","    'page': 6,\n","    'url': 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf#page=6'},\n","   {'doc_type': 'plan benefits',\n","    'company': 'essence',\n","    'source': '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf',\n","    'page': 6,\n","    'url': 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf#page=6'},\n","   {'doc_type': 'plan benefits',\n","    'company': 'essence',\n","    'source': '2023-EHI-SOBSummaryofBenefitsLOULEX.pdf',\n","    'page': 10,\n","    'url': 'https://shared.portals.lumeris.io/Document/Download?doc=/2023/EHI/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf#page=10'}]],\n"," 'distances': [[0.9116247892379761,\n","   0.9324960708618164,\n","   1.0074315071105957,\n","   1.0442452430725098,\n","   1.1675176620483398]]}"]},"metadata":{},"execution_count":72}]},{"cell_type":"markdown","source":["# commiting to git"],"metadata":{"id":"RgbFCCHG07h1"}},{"cell_type":"code","source":["!git status"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"hhzTKrm-0-Fn","executionInfo":{"status":"ok","timestamp":1678290364375,"user_tz":300,"elapsed":131,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"7e3f2f23-8923-4711-bd6f-49715201792f"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["On branch main\n","Your branch is up to date with 'origin/main'.\n","\n","Changes not staged for commit:\n","  (use \"git add <file>...\" to update what will be committed)\n","  (use \"git restore <file>...\" to discard changes in working directory)\n","\t\u001b[31mmodified:   app.py\u001b[m\n","\t\u001b[31mmodified:   data/mychromadb/chroma-collections.parquet\u001b[m\n","\t\u001b[31mmodified:   data/mychromadb/chroma-embeddings.parquet\u001b[m\n","\t\u001b[31mmodified:   doc_ingest.ipynb\u001b[m\n","\n","Untracked files:\n","  (use \"git add <file>...\" to include in what will be committed)\n","\t\u001b[31mdata/mychromadb/index/id_to_uuid_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[31mdata/mychromadb/index/id_to_uuid_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[31mdata/mychromadb/index/index_7b6e8b13-ff31-4891-860c-8c9cd380651e.bin\u001b[m\n","\t\u001b[31mdata/mychromadb/index/index_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.bin\u001b[m\n","\t\u001b[31mdata/mychromadb/index/index_metadata_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[31mdata/mychromadb/index/index_metadata_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[31mdata/mychromadb/index/uuid_to_id_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[31mdata/mychromadb/index/uuid_to_id_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[31mplan_docs/\u001b[m\n","\t\u001b[31mplan_metadata.xlsx\u001b[m\n","\t\u001b[31mplans.sqlite\u001b[m\n","\t\u001b[31msales_qa/\u001b[m\n","\n","no changes added to commit (use \"git add\" and/or \"git commit -a\")\n"]}]},{"cell_type":"code","source":["!git add plan_docs/* plan_metadata.xlsx plans.sqlite data/*"],"metadata":{"id":"FTda-h_H1Alo"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["!git status"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"DPq5dAFL5zpr","executionInfo":{"status":"ok","timestamp":1678290413812,"user_tz":300,"elapsed":1494,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"87c910bd-e8d5-4b09-f29a-45737b3edcba"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["On branch main\n","Your branch is up to date with 'origin/main'.\n","\n","Changes to be committed:\n","  (use \"git restore --staged <file>...\" to unstage)\n","\t\u001b[32mmodified:   data/mychromadb/chroma-collections.parquet\u001b[m\n","\t\u001b[32mmodified:   data/mychromadb/chroma-embeddings.parquet\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/id_to_uuid_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/id_to_uuid_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/index_7b6e8b13-ff31-4891-860c-8c9cd380651e.bin\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/index_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.bin\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/index_metadata_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/index_metadata_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/uuid_to_id_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\u001b[m\n","\t\u001b[32mnew file:   data/mychromadb/index/uuid_to_id_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\u001b[m\n","\t\u001b[32mnew file:   plan_docs/Essence/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf\u001b[m\n","\t\u001b[32mnew file:   plan_docs/Humana/H1036236000SB23.pdf\u001b[m\n","\t\u001b[32mnew file:   plan_docs/Humana/H5619071000SB23.pdf\u001b[m\n","\t\u001b[32mnew file:   plan_metadata.xlsx\u001b[m\n","\t\u001b[32mnew file:   plans.sqlite\u001b[m\n","\n","Changes not staged for commit:\n","  (use \"git add <file>...\" to update what will be committed)\n","  (use \"git restore <file>...\" to discard changes in working directory)\n","\t\u001b[31mmodified:   app.py\u001b[m\n","\t\u001b[31mmodified:   doc_ingest.ipynb\u001b[m\n","\n"]}]},{"cell_type":"code","source":["!git config --global user.email \"[email protected]\"\n","!git config --global user.name \"Michael Brown\""],"metadata":{"id":"UnF-t-BC6GiH"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# Hugging Face specific creds\n","username = 'mabrow05'\n","huggingface_api_key = ''"],"metadata":{"id":"URTckbOT6GwE"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"RMUzfcY96GyR"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["!git lfs install"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"LKfOVikH6G00","executionInfo":{"status":"ok","timestamp":1678291101751,"user_tz":300,"elapsed":1136,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"01abc380-47d8-41a8-bfb5-fd6f33f206da"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Updated git hooks.\n","Git LFS initialized.\n"]}]},{"cell_type":"code","source":["!git commit -am \"Added in essence healthcare plans\""],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"kx0fjiBL52He","executionInfo":{"status":"ok","timestamp":1678290523688,"user_tz":300,"elapsed":2668,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"765b2cc7-1340-4fb4-d74a-e4d993a97d98"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["fatal: cannot exec '.git/hooks/post-commit': Permission denied\n","[main cd9ef8e] Added in essence healthcare plans\n"," 17 files changed, 52 insertions(+), 11 deletions(-)\n"," create mode 100644 data/mychromadb/index/id_to_uuid_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\n"," create mode 100644 data/mychromadb/index/id_to_uuid_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\n"," create mode 100644 data/mychromadb/index/index_7b6e8b13-ff31-4891-860c-8c9cd380651e.bin\n"," create mode 100644 data/mychromadb/index/index_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.bin\n"," create mode 100644 data/mychromadb/index/index_metadata_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\n"," create mode 100644 data/mychromadb/index/index_metadata_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\n"," create mode 100644 data/mychromadb/index/uuid_to_id_7b6e8b13-ff31-4891-860c-8c9cd380651e.pkl\n"," create mode 100644 data/mychromadb/index/uuid_to_id_ab5c1c5b-bbc4-43cf-98cc-db6d450fe596.pkl\n"," rewrite doc_ingest.ipynb (77%)\n"," create mode 100644 plan_docs/Essence/2023-EHI-SOBSummaryofBenefitsLOULEX.pdf\n"," create mode 100644 plan_docs/Humana/H1036236000SB23.pdf\n"," create mode 100644 plan_docs/Humana/H5619071000SB23.pdf\n"," create mode 100644 plan_metadata.xlsx\n"," create mode 100644 plans.sqlite\n"]}]},{"cell_type":"code","source":["!git push"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"cRWr9pC46Aws","executionInfo":{"status":"ok","timestamp":1678291110666,"user_tz":300,"elapsed":1971,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"d6c12f67-69fd-4a9a-fa59-a507ca190c3d"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Uploading LFS objects:   0% (0/1), 0 B | 0 B/s\rbatch response: Repository not found\n","\u001b[31merror: failed to push some refs to 'https://mabrow05:[email protected]/spaces/mabrow05/sales_qa'\n","\u001b[m"]}]},{"cell_type":"code","source":["!ls -la .git/hooks\n","!chmod 777 .git/hooks/*"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Xxh1bl4D6UOr","executionInfo":{"status":"ok","timestamp":1678290945741,"user_tz":300,"elapsed":456,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"2f761004-8eda-4672-9072-263501d8c8e7"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["total 24\n","-rw------- 1 root root  478 Mar  7 21:23 applypatch-msg.sample\n","-rw------- 1 root root  896 Mar  7 21:23 commit-msg.sample\n","-rw------- 1 root root 3079 Mar  7 21:23 fsmonitor-watchman.sample\n","-rw------- 1 root root  280 Mar  8 15:46 post-checkout\n","-rw------- 1 root root  276 Mar  8 15:46 post-commit\n","-rw------- 1 root root  274 Mar  8 15:46 post-merge\n","-rw------- 1 root root  189 Mar  7 21:23 post-update.sample\n","-rw------- 1 root root  424 Mar  7 21:23 pre-applypatch.sample\n","-rw------- 1 root root 1638 Mar  7 21:23 pre-commit.sample\n","-rw------- 1 root root  416 Mar  7 21:23 pre-merge-commit.sample\n","-rw------- 1 root root 1492 Mar  7 21:23 prepare-commit-msg.sample\n","-rw------- 1 root root  270 Mar  8 15:46 pre-push\n","-rw------- 1 root root 1348 Mar  7 21:23 pre-push.sample\n","-rw------- 1 root root 4898 Mar  7 21:23 pre-rebase.sample\n","-rw------- 1 root root  544 Mar  7 21:23 pre-receive.sample\n","-rw------- 1 root root 3610 Mar  7 21:23 update.sample\n"]}]},{"cell_type":"code","source":["!ls -la .git/hooks"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3_tchio87eNT","executionInfo":{"status":"ok","timestamp":1678290947967,"user_tz":300,"elapsed":308,"user":{"displayName":"Michael Brown","userId":"08329931526666825911"}},"outputId":"158867cd-548f-4b9b-bc56-346467182d65"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["total 24\n","-rwx------ 1 root root  478 Mar  7 21:23 applypatch-msg.sample\n","-rwx------ 1 root root  896 Mar  7 21:23 commit-msg.sample\n","-rwx------ 1 root root 3079 Mar  7 21:23 fsmonitor-watchman.sample\n","-rwx------ 1 root root  280 Mar  8 15:46 post-checkout\n","-rwx------ 1 root root  276 Mar  8 15:46 post-commit\n","-rwx------ 1 root root  274 Mar  8 15:46 post-merge\n","-rwx------ 1 root root  189 Mar  7 21:23 post-update.sample\n","-rwx------ 1 root root  424 Mar  7 21:23 pre-applypatch.sample\n","-rwx------ 1 root root 1638 Mar  7 21:23 pre-commit.sample\n","-rwx------ 1 root root  416 Mar  7 21:23 pre-merge-commit.sample\n","-rwx------ 1 root root 1492 Mar  7 21:23 prepare-commit-msg.sample\n","-rwx------ 1 root root  270 Mar  8 15:46 pre-push\n","-rwx------ 1 root root 1348 Mar  7 21:23 pre-push.sample\n","-rwx------ 1 root root 4898 Mar  7 21:23 pre-rebase.sample\n","-rwx------ 1 root root  544 Mar  7 21:23 pre-receive.sample\n","-rwx------ 1 root root 3610 Mar  7 21:23 update.sample\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"cXlrq9Vr740w"},"execution_count":null,"outputs":[]}],"metadata":{"colab":{"provenance":[{"file_id":"https://github.com/gfhayworth/ama/blob/main/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb","timestamp":1660011228850}]},"kernelspec":{"display_name":"Python 3 (ipykernel)","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.8.8"},"widgets":{"application/vnd.jupyter.widget-state+json":{"b138aa06a9304d828d4aa804a63328e9":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_3163aa05a9fc48759843da21049db5c0","IPY_MODEL_802d51f993b24af0844960285b653700","IPY_MODEL_1886832bbc6e4b958166d932c6d0460e"],"layout":"IPY_MODEL_8d198fa250d84c958b6fcf1b49009bc8"}},"3163aa05a9fc48759843da21049db5c0":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_897aad10e1604127a1915f6a8c2939dc","placeholder":"​","style":"IPY_MODEL_3ce90b9ccda249c2af829f68cd2a669e","value":"Downloading (…)5fedf/.gitattributes: 100%"}},"802d51f993b24af0844960285b653700":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_4eb5a2f79fc44a7d840346fc389e8f65","max":737,"min":0,"orientation":"horizontal","style":"IPY_MODEL_5ec59a43860e4b4cb6e86c1bd87bace2","value":737}},"1886832bbc6e4b958166d932c6d0460e":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_e40239c169cc40dfbf156cdec3e9f6b7","placeholder":"​","style":"IPY_MODEL_c925f2e1ade241a595c7f1e0b7746fa7","value":" 737/737 [00:00&lt;00:00, 17.4kB/s]"}},"8d198fa250d84c958b6fcf1b49009bc8":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"897aad10e1604127a1915f6a8c2939dc":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3ce90b9ccda249c2af829f68cd2a669e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"4eb5a2f79fc44a7d840346fc389e8f65":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"5ec59a43860e4b4cb6e86c1bd87bace2":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"e40239c169cc40dfbf156cdec3e9f6b7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c925f2e1ade241a595c7f1e0b7746fa7":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"ec44a3ee0fde44d4bae2e7cf96984fb6":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_23266eca71064796b1114575a257604b","IPY_MODEL_1c01bc9a697044c2bbb42be8796fc4eb","IPY_MODEL_2de9485e0ddb4121b6c2af5d3cd80fa6"],"layout":"IPY_MODEL_7c091484eec042b3b26b550ce307bee3"}},"23266eca71064796b1114575a257604b":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_2651c98cce6648b1bc99f186513a399b","placeholder":"​","style":"IPY_MODEL_177bc8603ecd43b49546475211c7f868","value":"Downloading (…)_Pooling/config.json: 100%"}},"1c01bc9a697044c2bbb42be8796fc4eb":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_0c131542642148c9961536ea98c0137c","max":190,"min":0,"orientation":"horizontal","style":"IPY_MODEL_5071b88ecea54a1ea12a93e6fa68ae40","value":190}},"2de9485e0ddb4121b6c2af5d3cd80fa6":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f5b98acfc7cf42e0ab56ed2dc122ad70","placeholder":"​","style":"IPY_MODEL_b3541618004b400abed23d873fcf8129","value":" 190/190 [00:00&lt;00:00, 3.15kB/s]"}},"7c091484eec042b3b26b550ce307bee3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2651c98cce6648b1bc99f186513a399b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"177bc8603ecd43b49546475211c7f868":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"0c131542642148c9961536ea98c0137c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"5071b88ecea54a1ea12a93e6fa68ae40":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"f5b98acfc7cf42e0ab56ed2dc122ad70":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b3541618004b400abed23d873fcf8129":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"f0a3f17de8464aea8c0858a417954f73":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_58de80d177a84e4fa3cc24babcb51438","IPY_MODEL_9e83e4e3102b4f80a568a17f4b853926","IPY_MODEL_0830d86cd78a4b1cb385fe888f9e4343"],"layout":"IPY_MODEL_e88b7524a6b649f2b833ab407acd4653"}},"58de80d177a84e4fa3cc24babcb51438":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a0e3c6b268d1459987eed3090622b63f","placeholder":"​","style":"IPY_MODEL_cd73ae34c091463eaf721abaf57f8097","value":"Downloading (…)2cb455fedf/README.md: 100%"}},"9e83e4e3102b4f80a568a17f4b853926":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_6a8cb3f76eca40b69fb2d4c60fff9644","max":11520,"min":0,"orientation":"horizontal","style":"IPY_MODEL_da41b54262944ff8ab71318d4ae9c939","value":11520}},"0830d86cd78a4b1cb385fe888f9e4343":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_2285bf4d98d042ff998ca1e9ba468886","placeholder":"​","style":"IPY_MODEL_bf3db42846e8468892a9b9691cfe2b2a","value":" 11.5k/11.5k [00:00&lt;00:00, 450kB/s]"}},"e88b7524a6b649f2b833ab407acd4653":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a0e3c6b268d1459987eed3090622b63f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"cd73ae34c091463eaf721abaf57f8097":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6a8cb3f76eca40b69fb2d4c60fff9644":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"da41b54262944ff8ab71318d4ae9c939":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"2285bf4d98d042ff998ca1e9ba468886":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"bf3db42846e8468892a9b9691cfe2b2a":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"cc4ea8a17d994dd6afdecb21cfeaabae":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_4122d5897b0341f286e89526fc4bcf8b","IPY_MODEL_530e0568b08e4446a3a2d7825abe7c4a","IPY_MODEL_bdc82dc3774d4afba63f7cb3a648a4fe"],"layout":"IPY_MODEL_43789605cb504d729e4d0218feb264c5"}},"4122d5897b0341f286e89526fc4bcf8b":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_ba9b0333ca5b4ff38a3d233754557e90","placeholder":"​","style":"IPY_MODEL_49e93623b6a7482eabaa57aa022dc122","value":"Downloading (…)b455fedf/config.json: 100%"}},"530e0568b08e4446a3a2d7825abe7c4a":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_96468298aa014ce7a446a99935300099","max":612,"min":0,"orientation":"horizontal","style":"IPY_MODEL_92008b6a8dd14d729f4bdde224ee8ba1","value":612}},"bdc82dc3774d4afba63f7cb3a648a4fe":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f106e897ca324eb1adc3b54c6deaf6c9","placeholder":"​","style":"IPY_MODEL_57958cc4a57c4cb6b5a06d8ea5fd9a3c","value":" 612/612 [00:00&lt;00:00, 16.0kB/s]"}},"43789605cb504d729e4d0218feb264c5":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ba9b0333ca5b4ff38a3d233754557e90":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"49e93623b6a7482eabaa57aa022dc122":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"96468298aa014ce7a446a99935300099":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"92008b6a8dd14d729f4bdde224ee8ba1":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"f106e897ca324eb1adc3b54c6deaf6c9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"57958cc4a57c4cb6b5a06d8ea5fd9a3c":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"2f5c0d8a7cd94a86ac610d1a202afe91":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_ff938341c31248a4936a3712b1639365","IPY_MODEL_982d23e0c4e34fe88d725c36c6233490","IPY_MODEL_128edee01303462093110b5fa285e31f"],"layout":"IPY_MODEL_c45c3893cff44b948c10ccf2f579ef07"}},"ff938341c31248a4936a3712b1639365":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_419be37eac5f426dbb16d9851ba5bc67","placeholder":"​","style":"IPY_MODEL_105dafda8eaf48c19f07bf4fb81c9ba1","value":"Downloading (…)ce_transformers.json: 100%"}},"982d23e0c4e34fe88d725c36c6233490":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_bdd19651227542f3ac1720a681c03257","max":116,"min":0,"orientation":"horizontal","style":"IPY_MODEL_72ef20a366b34b50846c87c35a115750","value":116}},"128edee01303462093110b5fa285e31f":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_1f1324c56a524649ac70dacaf9c8f99d","placeholder":"​","style":"IPY_MODEL_452a4ef4f5834479b536770f38ea0023","value":" 116/116 [00:00&lt;00:00, 4.17kB/s]"}},"c45c3893cff44b948c10ccf2f579ef07":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"419be37eac5f426dbb16d9851ba5bc67":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"105dafda8eaf48c19f07bf4fb81c9ba1":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"bdd19651227542f3ac1720a681c03257":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"72ef20a366b34b50846c87c35a115750":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"1f1324c56a524649ac70dacaf9c8f99d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"452a4ef4f5834479b536770f38ea0023":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"313a969fb7404f7ab03d3e510c5d901d":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_722ca54383bd45c698c92725622cc5a9","IPY_MODEL_57ed3b1684044e40a87856254c2209b6","IPY_MODEL_572ebca45077443aac1ad00b16445aee"],"layout":"IPY_MODEL_fc2711786fbf46cd86b40356b174edb7"}},"722ca54383bd45c698c92725622cc5a9":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_3b6af6f90b0d4f4899d6736e9970e845","placeholder":"​","style":"IPY_MODEL_331623885aab458db43c5b8523f11e1b","value":"Downloading (…)edf/data_config.json: 100%"}},"57ed3b1684044e40a87856254c2209b6":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_76234ada88a14a39815261ae69df8b58","max":25457,"min":0,"orientation":"horizontal","style":"IPY_MODEL_cac81ef5f6494672a685e887f710bd3b","value":25457}},"572ebca45077443aac1ad00b16445aee":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_ae4c84c9644044458deabb8cc44b1484","placeholder":"​","style":"IPY_MODEL_766538d72846478ea077c99b90227e67","value":" 25.5k/25.5k [00:00&lt;00:00, 539kB/s]"}},"fc2711786fbf46cd86b40356b174edb7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3b6af6f90b0d4f4899d6736e9970e845":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"331623885aab458db43c5b8523f11e1b":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"76234ada88a14a39815261ae69df8b58":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"cac81ef5f6494672a685e887f710bd3b":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"ae4c84c9644044458deabb8cc44b1484":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"766538d72846478ea077c99b90227e67":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"19c051868b08475dbe5f3b0dd6d6e060":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_811f85a540624291a4447c8486d0689e","IPY_MODEL_2ab11e53a1ef4cad8bc715323a27e564","IPY_MODEL_7d46fda7ba5447dda9c20923c99316b3"],"layout":"IPY_MODEL_463bbd9f8f314654a2c04158199e0d3a"}},"811f85a540624291a4447c8486d0689e":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_59902eb789434a33afdfb95010ba94c2","placeholder":"​","style":"IPY_MODEL_351cc2ed2c1c401c894079892c66385e","value":"Downloading pytorch_model.bin: 100%"}},"2ab11e53a1ef4cad8bc715323a27e564":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_b0dce9de32ee4764961b34f186fed478","max":90888945,"min":0,"orientation":"horizontal","style":"IPY_MODEL_0e60bd79772743f380804c5062751e5c","value":90888945}},"7d46fda7ba5447dda9c20923c99316b3":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_962edf0e1af54ab6b4cd4a0657293721","placeholder":"​","style":"IPY_MODEL_53f252e74ac447e4bc26f1fdaed9b115","value":" 90.9M/90.9M [00:00&lt;00:00, 138MB/s]"}},"463bbd9f8f314654a2c04158199e0d3a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"59902eb789434a33afdfb95010ba94c2":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"351cc2ed2c1c401c894079892c66385e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b0dce9de32ee4764961b34f186fed478":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0e60bd79772743f380804c5062751e5c":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"962edf0e1af54ab6b4cd4a0657293721":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"53f252e74ac447e4bc26f1fdaed9b115":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"ca5074be81cb47b1941dad04caf87c65":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f952d97cfda94aa9bb86f6cb7ef36aa2","IPY_MODEL_11b0350ded3b46bc9f1165dcea2e5d45","IPY_MODEL_5e6be0a4986d49eabf2af04209f41199"],"layout":"IPY_MODEL_bf6e6b27866b436ebaf88e5708e286ab"}},"f952d97cfda94aa9bb86f6cb7ef36aa2":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_39eb5c90bd684c44920af2bf9aa09717","placeholder":"​","style":"IPY_MODEL_0b8be20124e74782927c0e5153790c0b","value":"Downloading (…)nce_bert_config.json: 100%"}},"11b0350ded3b46bc9f1165dcea2e5d45":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_a5e84329dbc7483cb06990cab5ef0f1b","max":53,"min":0,"orientation":"horizontal","style":"IPY_MODEL_54e2256e878d4066971e659826c6da60","value":53}},"5e6be0a4986d49eabf2af04209f41199":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_1ba572ad1fb9452a96c0f30e9d981334","placeholder":"​","style":"IPY_MODEL_ccd05565f8284fb2b4f82123f6132544","value":" 53.0/53.0 [00:00&lt;00:00, 682B/s]"}},"bf6e6b27866b436ebaf88e5708e286ab":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"39eb5c90bd684c44920af2bf9aa09717":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0b8be20124e74782927c0e5153790c0b":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a5e84329dbc7483cb06990cab5ef0f1b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"54e2256e878d4066971e659826c6da60":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"1ba572ad1fb9452a96c0f30e9d981334":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ccd05565f8284fb2b4f82123f6132544":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"afffdf68830840feb2ab6fd307f71494":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_4bab0d0fe5554221b5bd35e4dfd6c290","IPY_MODEL_ba551fb0cd49461e8f13b67612f65993","IPY_MODEL_f140e4b6fc48424aac34fc009d4374a4"],"layout":"IPY_MODEL_d6966de0903e47788a8c3dd422a1df1c"}},"4bab0d0fe5554221b5bd35e4dfd6c290":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_80bdf38dbcae4e03a7b1fde210933a52","placeholder":"​","style":"IPY_MODEL_50309917f4884787a5ff8eeae893a1b4","value":"Downloading (…)cial_tokens_map.json: 100%"}},"ba551fb0cd49461e8f13b67612f65993":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_055048a8b16e42f69baad57e438f9c5e","max":112,"min":0,"orientation":"horizontal","style":"IPY_MODEL_00defac0a3844677a439823caeaeb5cb","value":112}},"f140e4b6fc48424aac34fc009d4374a4":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_14029eaf55a44a1a863764b815c2b07b","placeholder":"​","style":"IPY_MODEL_043a7d73810f47cbab03e89c93cfaa91","value":" 112/112 [00:00&lt;00:00, 1.92kB/s]"}},"d6966de0903e47788a8c3dd422a1df1c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"80bdf38dbcae4e03a7b1fde210933a52":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"50309917f4884787a5ff8eeae893a1b4":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"055048a8b16e42f69baad57e438f9c5e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"00defac0a3844677a439823caeaeb5cb":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"14029eaf55a44a1a863764b815c2b07b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"043a7d73810f47cbab03e89c93cfaa91":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"32528eb2f60d40cb8e5fc74ba976345e":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_593a1d80de49408d81f776c1d2c7faea","IPY_MODEL_891f1b01646b49c48bd05053df1fef16","IPY_MODEL_43e174cff8f64c4783a9f1e3a5391201"],"layout":"IPY_MODEL_54f01a1ab4e8400fa73c59b8603a4378"}},"593a1d80de49408d81f776c1d2c7faea":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a461847f45cb4fb7bf398c6ed7dd910f","placeholder":"​","style":"IPY_MODEL_bdce7da8e16b4c8d9579232a9360c1a6","value":"Downloading (…)5fedf/tokenizer.json: 100%"}},"891f1b01646b49c48bd05053df1fef16":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_6f3c94d707a048e2b56b753e2cff884a","max":466247,"min":0,"orientation":"horizontal","style":"IPY_MODEL_d4106d077a1d4a36b14e3b28e8b2a19c","value":466247}},"43e174cff8f64c4783a9f1e3a5391201":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_73e35bb344ab4e96b48e614b9d791047","placeholder":"​","style":"IPY_MODEL_6a0602071c3c44cdbbc8ba9496ef7dba","value":" 466k/466k [00:00&lt;00:00, 2.69MB/s]"}},"54f01a1ab4e8400fa73c59b8603a4378":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a461847f45cb4fb7bf398c6ed7dd910f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"bdce7da8e16b4c8d9579232a9360c1a6":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6f3c94d707a048e2b56b753e2cff884a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d4106d077a1d4a36b14e3b28e8b2a19c":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"73e35bb344ab4e96b48e614b9d791047":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6a0602071c3c44cdbbc8ba9496ef7dba":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a53a60056c87417eba56660294b39ba7":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_ac27b3a70e9c46ffa5fee81159632b60","IPY_MODEL_abb28254a1b4446c8181364892da547d","IPY_MODEL_45989b5303c243978757bb64cbbfb24c"],"layout":"IPY_MODEL_402924ab2cdf4152bb2b0e2e07373c03"}},"ac27b3a70e9c46ffa5fee81159632b60":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_aa1c9838fbf846f991a8c8b4aac6ad73","placeholder":"​","style":"IPY_MODEL_772746054aff45c9bb2e11af14249cff","value":"Downloading (…)okenizer_config.json: 100%"}},"abb28254a1b4446c8181364892da547d":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_a5a07686ee9c466586d0053bb178ebc4","max":383,"min":0,"orientation":"horizontal","style":"IPY_MODEL_382cbe2fcb3c4a27bc5347cf15c7d2fc","value":383}},"45989b5303c243978757bb64cbbfb24c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_6b63577927ac45008f4bbd51ac6f75d0","placeholder":"​","style":"IPY_MODEL_dd2168b61f0a4af286cc4d0c0c6f3a44","value":" 383/383 [00:00&lt;00:00, 4.80kB/s]"}},"402924ab2cdf4152bb2b0e2e07373c03":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"aa1c9838fbf846f991a8c8b4aac6ad73":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"772746054aff45c9bb2e11af14249cff":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a5a07686ee9c466586d0053bb178ebc4":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"382cbe2fcb3c4a27bc5347cf15c7d2fc":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"6b63577927ac45008f4bbd51ac6f75d0":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"dd2168b61f0a4af286cc4d0c0c6f3a44":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"93fc525e43d64f35b5278cfbdffa8b3e":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_9871d3b3b2414179b0a979fbadc1d3ee","IPY_MODEL_8e85290f8d6a420591e5655c638c31e4","IPY_MODEL_785acd5dd38f481483afe92c1ddcd496"],"layout":"IPY_MODEL_bfece0017b914c96bdafccf921d6ab8b"}},"9871d3b3b2414179b0a979fbadc1d3ee":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_2122594f781a4cefa903bc8b5c826b77","placeholder":"​","style":"IPY_MODEL_dcfe5fa3b505427f96273b24c35618fd","value":"Downloading (…)fedf/train_script.py: 100%"}},"8e85290f8d6a420591e5655c638c31e4":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_cdcd9f35d5af4b7992266f5f12e6a66f","max":13846,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c38c65f297ff4b2a9d864e10049de670","value":13846}},"785acd5dd38f481483afe92c1ddcd496":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_ac17747a2f1e40ca8f8a724280fde72a","placeholder":"​","style":"IPY_MODEL_b090df0e82b144f680f9758300bf475b","value":" 13.8k/13.8k [00:00&lt;00:00, 279kB/s]"}},"bfece0017b914c96bdafccf921d6ab8b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2122594f781a4cefa903bc8b5c826b77":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"dcfe5fa3b505427f96273b24c35618fd":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"cdcd9f35d5af4b7992266f5f12e6a66f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c38c65f297ff4b2a9d864e10049de670":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"ac17747a2f1e40ca8f8a724280fde72a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b090df0e82b144f680f9758300bf475b":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"55c89cb46a744f909da5cfffe254bbc3":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_1bc885119d374107896e65f34e9195fb","IPY_MODEL_7639eab1ff5a4fd08ef2fea77af624b0","IPY_MODEL_90d3330947a24f5f87e7f001c45e563c"],"layout":"IPY_MODEL_ed876d27136d45859c7a2f250f714f89"}},"1bc885119d374107896e65f34e9195fb":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_1aa841d3489b4a0aad8d03af1db9d431","placeholder":"​","style":"IPY_MODEL_d86c8b087abd4c4a8f0025bb62a2d968","value":"Downloading (…)2cb455fedf/vocab.txt: 100%"}},"7639eab1ff5a4fd08ef2fea77af624b0":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_b71a8d721ad947278ea9eb50640ed642","max":231508,"min":0,"orientation":"horizontal","style":"IPY_MODEL_8c98e217657e4424bb80bb1bec27815f","value":231508}},"90d3330947a24f5f87e7f001c45e563c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_58aa5e0dbd774c9ca49c876b3335d405","placeholder":"​","style":"IPY_MODEL_2ff08d3beb1444c9977a6bde470e40ac","value":" 232k/232k [00:00&lt;00:00, 1.36MB/s]"}},"ed876d27136d45859c7a2f250f714f89":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1aa841d3489b4a0aad8d03af1db9d431":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d86c8b087abd4c4a8f0025bb62a2d968":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b71a8d721ad947278ea9eb50640ed642":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8c98e217657e4424bb80bb1bec27815f":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"58aa5e0dbd774c9ca49c876b3335d405":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2ff08d3beb1444c9977a6bde470e40ac":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a0dd1a2336ac499f8059a920d29ff8f2":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_e7e356b52dee40d58422e10b7fadcdce","IPY_MODEL_7d05d2d945e44c6097c90ddb60135497","IPY_MODEL_280811af738848469324c8f6fa5ba349"],"layout":"IPY_MODEL_f441ae1f11c74ab7bde13204b4f94ab4"}},"e7e356b52dee40d58422e10b7fadcdce":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_9e5c0e875f1c4df49e076600aa07c27d","placeholder":"​","style":"IPY_MODEL_d52138057e8c4689a370439000244b25","value":"Downloading (…)455fedf/modules.json: 100%"}},"7d05d2d945e44c6097c90ddb60135497":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_b180984828aa4418b8a6fc3b6f238ff1","max":349,"min":0,"orientation":"horizontal","style":"IPY_MODEL_22b8df67284e489ab06dea21de80ba07","value":349}},"280811af738848469324c8f6fa5ba349":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f102594506c0474590147761fbd7ece4","placeholder":"​","style":"IPY_MODEL_8a5c19af1c854d4ab27f20fec023bc35","value":" 349/349 [00:00&lt;00:00, 4.22kB/s]"}},"f441ae1f11c74ab7bde13204b4f94ab4":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"9e5c0e875f1c4df49e076600aa07c27d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d52138057e8c4689a370439000244b25":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b180984828aa4418b8a6fc3b6f238ff1":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"22b8df67284e489ab06dea21de80ba07":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"f102594506c0474590147761fbd7ece4":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8a5c19af1c854d4ab27f20fec023bc35":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"5d41e7c4c7cf4eff932b0b7d245003bb":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_b191e73abc0e4064b146e6b143c27c7f","IPY_MODEL_d232c51e5ff04332abce4e4029616089","IPY_MODEL_812e7ce0577c48ae8d7dc55f35da6a2f"],"layout":"IPY_MODEL_ab0c84ed814548a792a4b8295986ae27"}},"b191e73abc0e4064b146e6b143c27c7f":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_908102cf75904ef68efcd27498b6bd5f","placeholder":"​","style":"IPY_MODEL_6214ec5f027c4fee8651fdcfa64a3c59","value":"Batches: 100%"}},"d232c51e5ff04332abce4e4029616089":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_04ec9d98e8c14c97ab8453b5cb7b196f","max":49,"min":0,"orientation":"horizontal","style":"IPY_MODEL_a6c905aa92614362bff4a874fcb214f8","value":49}},"812e7ce0577c48ae8d7dc55f35da6a2f":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f7a195fe58934cb487daf4053b97c266","placeholder":"​","style":"IPY_MODEL_3be5dfec2f674e48ad23cf43624dfd44","value":" 49/49 [01:05&lt;00:00,  1.88it/s]"}},"ab0c84ed814548a792a4b8295986ae27":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"908102cf75904ef68efcd27498b6bd5f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6214ec5f027c4fee8651fdcfa64a3c59":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"04ec9d98e8c14c97ab8453b5cb7b196f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a6c905aa92614362bff4a874fcb214f8":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"f7a195fe58934cb487daf4053b97c266":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3be5dfec2f674e48ad23cf43624dfd44":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}},"gpuClass":"standard"},"nbformat":4,"nbformat_minor":0}