spacy.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: spacy in ./.venv/lib/python3.12/site-packages (3.7.6)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in ./.venv/lib/python3.12/site-packages (from spacy) (3.0.12)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in ./.venv/lib/python3.12/site-packages (from spacy) (1.0.5)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in ./.venv/lib/python3.12/site-packages (from spacy) (1.0.10)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in ./.venv/lib/python3.12/site-packages (from spacy) (2.0.8)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in ./.venv/lib/python3.12/site-packages (from spacy) (3.0.9)\n",
      "Requirement already satisfied: thinc<8.3.0,>=8.2.2 in ./.venv/lib/python3.12/site-packages (from spacy) (8.2.5)\n",
      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in ./.venv/lib/python3.12/site-packages (from spacy) (1.1.3)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in ./.venv/lib/python3.12/site-packages (from spacy) (2.4.8)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in ./.venv/lib/python3.12/site-packages (from spacy) (2.0.10)\n",
      "Requirement already satisfied: weasel<0.5.0,>=0.1.0 in ./.venv/lib/python3.12/site-packages (from spacy) (0.4.1)\n",
      "Requirement already satisfied: typer<1.0.0,>=0.3.0 in ./.venv/lib/python3.12/site-packages (from spacy) (0.12.5)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in ./.venv/lib/python3.12/site-packages (from spacy) (4.66.5)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in ./.venv/lib/python3.12/site-packages (from spacy) (2.32.3)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in ./.venv/lib/python3.12/site-packages (from spacy) (2.8.2)\n",
      "Requirement already satisfied: jinja2 in ./.venv/lib/python3.12/site-packages (from spacy) (3.1.4)\n",
      "Requirement already satisfied: setuptools in ./.venv/lib/python3.12/site-packages (from spacy) (74.1.2)\n",
      "Requirement already satisfied: packaging>=20.0 in ./.venv/lib/python3.12/site-packages (from spacy) (24.1)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in ./.venv/lib/python3.12/site-packages (from spacy) (3.4.0)\n",
      "Requirement already satisfied: numpy>=1.19.0 in ./.venv/lib/python3.12/site-packages (from spacy) (1.26.4)\n",
      "Requirement already satisfied: language-data>=1.2 in ./.venv/lib/python3.12/site-packages (from langcodes<4.0.0,>=3.2.0->spacy) (1.2.0)\n",
      "Requirement already satisfied: annotated-types>=0.4.0 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.7.0)\n",
      "Requirement already satisfied: pydantic-core==2.20.1 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (2.20.1)\n",
      "Requirement already satisfied: typing-extensions>=4.6.1 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (4.12.2)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.7)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2.2.2)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2024.7.4)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in ./.venv/lib/python3.12/site-packages (from thinc<8.3.0,>=8.2.2->spacy) (0.7.11)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in ./.venv/lib/python3.12/site-packages (from thinc<8.3.0,>=8.2.2->spacy) (0.1.5)\n",
      "Requirement already satisfied: click>=8.0.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (8.1.7)\n",
      "Requirement already satisfied: shellingham>=1.3.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (1.5.4)\n",
      "Requirement already satisfied: rich>=10.11.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (13.8.0)\n",
      "Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in ./.venv/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy) (0.19.0)\n",
      "Requirement already satisfied: smart-open<8.0.0,>=5.2.1 in ./.venv/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy) (7.0.4)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in ./.venv/lib/python3.12/site-packages (from jinja2->spacy) (2.1.5)\n",
      "Requirement already satisfied: marisa-trie>=0.7.7 in ./.venv/lib/python3.12/site-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy) (1.2.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in ./.venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in ./.venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (2.18.0)\n",
      "Requirement already satisfied: wrapt in ./.venv/lib/python3.12/site-packages (from smart-open<8.0.0,>=5.2.1->weasel<0.5.0,>=0.1.0->spacy) (1.16.0)\n",
      "Requirement already satisfied: mdurl~=0.1 in ./.venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (0.1.2)\n",
      "Collecting en-core-web-sm==3.7.1\n",
      "  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl (12.8 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.8/12.8 MB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:01\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: spacy<3.8.0,>=3.7.2 in ./.venv/lib/python3.12/site-packages (from en-core-web-sm==3.7.1) (3.7.6)\n",
      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.0.12)\n",
      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.0.5)\n",
      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.0.10)\n",
      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.0.8)\n",
      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.0.9)\n",
      "Requirement already satisfied: thinc<8.3.0,>=8.2.2 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (8.2.5)\n",
      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.1.3)\n",
      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.4.8)\n",
      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.0.10)\n",
      "Requirement already satisfied: weasel<0.5.0,>=0.1.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.4.1)\n",
      "Requirement already satisfied: typer<1.0.0,>=0.3.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.12.5)\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (4.66.5)\n",
      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.32.3)\n",
      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.8.2)\n",
      "Requirement already satisfied: jinja2 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.1.4)\n",
      "Requirement already satisfied: setuptools in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (74.1.2)\n",
      "Requirement already satisfied: packaging>=20.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (24.1)\n",
      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.4.0)\n",
      "Requirement already satisfied: numpy>=1.19.0 in ./.venv/lib/python3.12/site-packages (from spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.26.4)\n",
      "Requirement already satisfied: language-data>=1.2 in ./.venv/lib/python3.12/site-packages (from langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.2.0)\n",
      "Requirement already satisfied: annotated-types>=0.4.0 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.7.0)\n",
      "Requirement already satisfied: pydantic-core==2.20.1 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.20.1)\n",
      "Requirement already satisfied: typing-extensions>=4.6.1 in ./.venv/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (4.12.2)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.7)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.2.2)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in ./.venv/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2024.7.4)\n",
      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in ./.venv/lib/python3.12/site-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.7.11)\n",
      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in ./.venv/lib/python3.12/site-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.1.5)\n",
      "Requirement already satisfied: click>=8.0.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (8.1.7)\n",
      "Requirement already satisfied: shellingham>=1.3.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.5.4)\n",
      "Requirement already satisfied: rich>=10.11.0 in ./.venv/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (13.8.0)\n",
      "Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in ./.venv/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.19.0)\n",
      "Requirement already satisfied: smart-open<8.0.0,>=5.2.1 in ./.venv/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (7.0.4)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in ./.venv/lib/python3.12/site-packages (from jinja2->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.1.5)\n",
      "Requirement already satisfied: marisa-trie>=0.7.7 in ./.venv/lib/python3.12/site-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.2.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in ./.venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in ./.venv/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (2.18.0)\n",
      "Requirement already satisfied: wrapt in ./.venv/lib/python3.12/site-packages (from smart-open<8.0.0,>=5.2.1->weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (1.16.0)\n",
      "Requirement already satisfied: mdurl~=0.1 in ./.venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-sm==3.7.1) (0.1.2)\n",
      "\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n",
      "You can now load the package via spacy.load('en_core_web_sm')\n",
      "Collecting ipywidgets\n",
      "  Using cached ipywidgets-8.1.5-py3-none-any.whl.metadata (2.3 kB)\n",
      "Requirement already satisfied: comm>=0.1.3 in ./.venv/lib/python3.12/site-packages (from ipywidgets) (0.2.2)\n",
      "Requirement already satisfied: ipython>=6.1.0 in ./.venv/lib/python3.12/site-packages (from ipywidgets) (8.27.0)\n",
      "Requirement already satisfied: traitlets>=4.3.1 in ./.venv/lib/python3.12/site-packages (from ipywidgets) (5.14.3)\n",
      "Collecting widgetsnbextension~=4.0.12 (from ipywidgets)\n",
      "  Using cached widgetsnbextension-4.0.13-py3-none-any.whl.metadata (1.6 kB)\n",
      "Collecting jupyterlab-widgets~=3.0.12 (from ipywidgets)\n",
      "  Using cached jupyterlab_widgets-3.0.13-py3-none-any.whl.metadata (4.1 kB)\n",
      "Requirement already satisfied: decorator in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (5.1.1)\n",
      "Requirement already satisfied: jedi>=0.16 in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (0.19.1)\n",
      "Requirement already satisfied: matplotlib-inline in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (0.1.7)\n",
      "Requirement already satisfied: prompt-toolkit<3.1.0,>=3.0.41 in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (3.0.47)\n",
      "Requirement already satisfied: pygments>=2.4.0 in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (2.18.0)\n",
      "Requirement already satisfied: stack-data in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (0.6.3)\n",
      "Requirement already satisfied: pexpect>4.3 in ./.venv/lib/python3.12/site-packages (from ipython>=6.1.0->ipywidgets) (4.9.0)\n",
      "Requirement already satisfied: parso<0.9.0,>=0.8.3 in ./.venv/lib/python3.12/site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets) (0.8.4)\n",
      "Requirement already satisfied: ptyprocess>=0.5 in ./.venv/lib/python3.12/site-packages (from pexpect>4.3->ipython>=6.1.0->ipywidgets) (0.7.0)\n",
      "Requirement already satisfied: wcwidth in ./.venv/lib/python3.12/site-packages (from prompt-toolkit<3.1.0,>=3.0.41->ipython>=6.1.0->ipywidgets) (0.2.13)\n",
      "Requirement already satisfied: executing>=1.2.0 in ./.venv/lib/python3.12/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.1.0)\n",
      "Requirement already satisfied: asttokens>=2.1.0 in ./.venv/lib/python3.12/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.4.1)\n",
      "Requirement already satisfied: pure-eval in ./.venv/lib/python3.12/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.2.3)\n",
      "Requirement already satisfied: six>=1.12.0 in ./.venv/lib/python3.12/site-packages (from asttokens>=2.1.0->stack-data->ipython>=6.1.0->ipywidgets) (1.16.0)\n",
      "Using cached ipywidgets-8.1.5-py3-none-any.whl (139 kB)\n",
      "Using cached jupyterlab_widgets-3.0.13-py3-none-any.whl (214 kB)\n",
      "Using cached widgetsnbextension-4.0.13-py3-none-any.whl (2.3 MB)\n",
      "Installing collected packages: widgetsnbextension, jupyterlab-widgets, ipywidgets\n",
      "Successfully installed ipywidgets-8.1.5 jupyterlab-widgets-3.0.13 widgetsnbextension-4.0.13\n"
     ]
    }
   ],
   "source": [
    "!pip install spacy\n",
    "!python -m spacy download en_core_web_sm\n",
    "!pip install ipywidgets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import spacy\n",
    "import dotenv\n",
    "from rich.console import Console\n",
    "\n",
    "import web_rag as wr\n",
    "import web_crawler as wc\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "console = Console()\n",
    "dotenv.load_dotenv()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not spacy.util.is_package(\"en_core_web_sm\"):\n",
    "    print(\"Downloading en_core_web_sm model...\")\n",
    "    spacy.cli.download(\"en_core_web_sm\")\n",
    "    print(\"Model downloaded successfully!\")\n",
    "nlp = spacy.load(\"en_core_web_sm\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "chat, embedding_model = wr.get_models(\"openai\", \"gpt-4o-mini\", 0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Elizabeth Holmes trial verdict guilty\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Elizabeth Holmes trial verdict guilty\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datetime import date\n",
    "today = date.today().strftime(\"%B %d, %Y\")\n",
    "query = f\"Is Elizabeth Holmes guilty?\"\n",
    "optimized_search_query = wr.optimize_search_query(chat, query)\n",
    "console.print(optimized_search_query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">retrieved <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span> contents\n",
       "</pre>\n"
      ],
      "text/plain": [
       "retrieved \u001b[1;36m5\u001b[0m contents\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sources = wc.get_sources(optimized_search_query, max_pages=5)\n",
    "contents = wc.get_links_contents(sources)\n",
    "console.print(f\"retrieved {len(contents)} contents\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/6k/6b1pw86x1yvc1_ds42gc1ms80000gq/T/ipykernel_7568/1451878299.py:13: UserWarning: [W007] The model you're using has no word vectors loaded, so the result of the Doc.similarity method will be based on the tagger, parser and NER, which may not give useful similarity judgements. This may happen if you're using one of the small models, e.g. `en_core_web_sm`, which don't ship with word vectors and only use context-sensitive tensors. You can always add your own word vectors, or use one of the larger models instead if available.\n",
      "  if prev_sent.similarity(curr_sent) >= similarity_threshold:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Created <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">115</span> semantic chunks\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Created \u001b[1;36m115\u001b[0m semantic chunks\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Sample chunk:\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Sample chunk:\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "    <span style=\"color: #008000; text-decoration-color: #008000\">'text'</span>: <span style=\"color: #008000; text-decoration-color: #008000\">\"Theranos founder Elizabeth Holmes was sentenced Friday to more than 11 years in prison for fraud after</span>\n",
       "<span style=\"color: #008000; text-decoration-color: #008000\">deceiving investors about the purported efficacy of her company's blood-testing technology.\"</span>,\n",
       "    <span style=\"color: #008000; text-decoration-color: #008000\">'metadata'</span>: <span style=\"font-weight: bold\">{</span>\n",
       "        <span style=\"color: #008000; text-decoration-color: #008000\">'title'</span>: <span style=\"color: #008000; text-decoration-color: #008000\">'Theranos founder Elizabeth Holmes sentenced to more than 11 years in prison'</span>,\n",
       "        <span style=\"color: #008000; text-decoration-color: #008000\">'source'</span>: \n",
       "<span style=\"color: #008000; text-decoration-color: #008000\">'https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.htm</span>\n",
       "<span style=\"color: #008000; text-decoration-color: #008000\">l'</span>\n",
       "    <span style=\"font-weight: bold\">}</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "    \u001b[32m'text'\u001b[0m: \u001b[32m\"Theranos founder Elizabeth Holmes was sentenced Friday to more than 11 years in prison for fraud after\u001b[0m\n",
       "\u001b[32mdeceiving investors about the purported efficacy of her company's blood-testing technology.\"\u001b[0m,\n",
       "    \u001b[32m'metadata'\u001b[0m: \u001b[1m{\u001b[0m\n",
       "        \u001b[32m'title'\u001b[0m: \u001b[32m'Theranos founder Elizabeth Holmes sentenced to more than 11 years in prison'\u001b[0m,\n",
       "        \u001b[32m'source'\u001b[0m: \n",
       "\u001b[32m'https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.htm\u001b[0m\n",
       "\u001b[32ml'\u001b[0m\n",
       "    \u001b[1m}\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from itertools import groupby\n",
    "from operator import itemgetter\n",
    "\n",
    "def group_similar_sentences(sentences, similarity_threshold=0.5):\n",
    "    grouped_sentences = []\n",
    "    for i, sentence in enumerate(sentences):\n",
    "        if i == 0:\n",
    "            grouped_sentences.append([sentence])\n",
    "        else:\n",
    "            prev_group = grouped_sentences[-1]\n",
    "            prev_sent = nlp(' '.join([s.text for s in prev_group]))\n",
    "            curr_sent = nlp(sentence.text)\n",
    "            if prev_sent.similarity(curr_sent) >= similarity_threshold:\n",
    "                prev_group.append(sentence)\n",
    "            else:\n",
    "                grouped_sentences.append([sentence])\n",
    "    return grouped_sentences\n",
    "\n",
    "# Initialize an empty list to store the semantically split content\n",
    "semantic_chunks = []\n",
    "\n",
    "# Iterate through the contents\n",
    "for content in contents:\n",
    "    # Extract the page content\n",
    "    page_content = content.get('page_content', '')\n",
    "    \n",
    "    if page_content:\n",
    "        # Process the text with spaCy\n",
    "        doc = nlp(page_content)\n",
    "        \n",
    "        # Split the content into sentences\n",
    "        sentences = list(doc.sents)\n",
    "        \n",
    "        # Group similar sentences\n",
    "        grouped_sentences = group_similar_sentences(sentences)\n",
    "        \n",
    "        for group in grouped_sentences:\n",
    "            # Create a chunk with the grouped sentences and metadata\n",
    "            chunk = {\n",
    "                'text': ' '.join([sent.text for sent in group]),\n",
    "                'metadata': {\n",
    "                    'title': content.get('title', ''),\n",
    "                    'source': content.get('link', '')\n",
    "                }\n",
    "            }\n",
    "            semantic_chunks.append(chunk)\n",
    "\n",
    "# Print the number of semantic chunks created\n",
    "console.print(f\"Created {len(semantic_chunks)} semantic chunks\")\n",
    "\n",
    "# Optionally, print a sample chunk to verify the structure\n",
    "if semantic_chunks:\n",
    "    console.print(\"Sample chunk:\")\n",
    "    console.print(semantic_chunks[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (1591802571.py, line 33)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  Cell \u001b[0;32mIn[103], line 33\u001b[0;36m\u001b[0m\n\u001b[0;31m    sents, vecs = process(contents[0].)\u001b[0m\n\u001b[0m                                      ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import spacy\n",
    "\n",
    "# Load the Spacy model\n",
    "nlp = spacy.load('en_core_web_sm')\n",
    "\n",
    "def process(text):\n",
    "    doc = nlp(text)\n",
    "    sents = list(doc.sents)\n",
    "    vecs = np.stack([sent.vector / sent.vector_norm for sent in sents])\n",
    "\n",
    "    return sents, vecs\n",
    "\n",
    "def cluster_text(sents, vecs, threshold):\n",
    "    clusters = [[0]]\n",
    "    for i in range(1, len(sents)):\n",
    "        if np.dot(vecs[i], vecs[i-1]) < threshold:\n",
    "            clusters.append([])\n",
    "        clusters[-1].append(i)\n",
    "    \n",
    "    return clusters\n",
    "\n",
    "def clean_text(text):\n",
    "    # Add your text cleaning process here\n",
    "    return text\n",
    "\n",
    "# Initialize the clusters lengths list and final texts list\n",
    "clusters_lens = []\n",
    "final_texts = []\n",
    "\n",
    "# Process the chunk\n",
    "threshold = 0.3\n",
    "sents, vecs = process(contents[0].)\n",
    "\n",
    "# Cluster the sentences\n",
    "clusters = cluster_text(sents, vecs, threshold)\n",
    "\n",
    "for cluster in clusters:\n",
    "    cluster_txt = clean_text(' '.join([sents[i].text for i in cluster]))\n",
    "    cluster_len = len(cluster_txt)\n",
    "    \n",
    "    # Check if the cluster is too short\n",
    "    if cluster_len < 60:\n",
    "        continue\n",
    "    \n",
    "    # Check if the cluster is too long\n",
    "    elif cluster_len > 3000:\n",
    "        threshold = 0.6\n",
    "        sents_div, vecs_div = process(cluster_txt)\n",
    "        reclusters = cluster_text(sents_div, vecs_div, threshold)\n",
    "        \n",
    "        for subcluster in reclusters:\n",
    "            div_txt = clean_text(' '.join([sents_div[i].text for i in subcluster]))\n",
    "            div_len = len(div_txt)\n",
    "            \n",
    "            if div_len < 60 or div_len > 3000:\n",
    "                continue\n",
    "            \n",
    "            clusters_lens.append(div_len)\n",
    "            final_texts.append(div_txt)\n",
    "            \n",
    "    else:\n",
    "        clusters_lens.append(cluster_len)\n",
    "        final_texts.append(cluster_txt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/6k/6b1pw86x1yvc1_ds42gc1ms80000gq/T/ipykernel_7568/342810436.py:8: UserWarning: [W007] The model you're using has no word vectors loaded, so the result of the Doc.similarity method will be based on the tagger, parser and NER, which may not give useful similarity judgements. This may happen if you're using one of the small models, e.g. `en_core_web_sm`, which don't ship with word vectors and only use context-sensitive tensors. You can always add your own word vectors, or use one of the larger models instead if available.\n",
      "  similarity = query_doc.similarity(chunk_doc)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Found <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8</span> relevant chunks\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Found \u001b[1;36m8\u001b[0m relevant chunks\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "Top relevant chunks:\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "Top relevant chunks:\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>. Similarity: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.6973</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "\u001b[1;36m1\u001b[0m. Similarity: \u001b[1;36m0.6973\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Text: Related Content\n",
       "Press Release\n",
       "SAN JOSE – Elizabeth A. Holmes was sentenced today to <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">135</span> months <span style=\"font-weight: bold\">(</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> years, <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span> months<span style=\"font-weight: bold\">)</span> in federal prison for \n",
       "defrauding investors in Theranos, Inc. of hundreds of millions of dollars, announced United States Attorney \n",
       "Stephanie M. Hinds, Federal Bureau of Investigation Special Agent in Charge Robert K. Tripp, Food and Drug \n",
       "Administration <span style=\"font-weight: bold\">(</span>FDA<span style=\"font-weight: bold\">)</span> Assistant Commissioner for Criminal Investigations Catherine A. Hermsen, and U.S. Postal \n",
       "Inspection Service <span style=\"font-weight: bold\">(</span>USPIS<span style=\"font-weight: bold\">)</span> San Francisco Division Acting Inspector in Charge Kevin Rho. The sentence was handed \n",
       "down by United States District Judge Edward J. Davila.\n",
       " “Silicon Valley has seen the rise of companies whose inventions have changed the world and, through intellectual \n",
       "prowess, hard work, and sheer determination, this region continues to innovate,” said U.S. Attorney Stephanie M. \n",
       "Hinds.\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Text: Related Content\n",
       "Press Release\n",
       "SAN JOSE – Elizabeth A. Holmes was sentenced today to \u001b[1;36m135\u001b[0m months \u001b[1m(\u001b[0m\u001b[1;36m11\u001b[0m years, \u001b[1;36m3\u001b[0m months\u001b[1m)\u001b[0m in federal prison for \n",
       "defrauding investors in Theranos, Inc. of hundreds of millions of dollars, announced United States Attorney \n",
       "Stephanie M. Hinds, Federal Bureau of Investigation Special Agent in Charge Robert K. Tripp, Food and Drug \n",
       "Administration \u001b[1m(\u001b[0mFDA\u001b[1m)\u001b[0m Assistant Commissioner for Criminal Investigations Catherine A. Hermsen, and U.S. Postal \n",
       "Inspection Service \u001b[1m(\u001b[0mUSPIS\u001b[1m)\u001b[0m San Francisco Division Acting Inspector in Charge Kevin Rho. The sentence was handed \n",
       "down by United States District Judge Edward J. Davila.\n",
       " “Silicon Valley has seen the rise of companies whose inventions have changed the world and, through intellectual \n",
       "prowess, hard work, and sheer determination, this region continues to innovate,” said U.S. Attorney Stephanie M. \n",
       "Hinds.\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Source: \n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Source: \n",
       "\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred\u001b[0m\n",
       "\u001b[4;94ms\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Title: Northern District of California | Elizabeth Holmes Sentenced To More Than <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Title: Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[1;36m11\u001b[0m Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span>. Similarity: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.6427</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "\u001b[1;36m2\u001b[0m. Similarity: \u001b[1;36m0.6427\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Text: The FBI is committed to investigating corporate fraud and working with our partners to help keep our capital \n",
       "markets working effectively,” said FBI Special Agent in Charge Robert K. Tripp. “The FBI and our partners worked \n",
       "tirelessly on this multi-year case and are proud justice has been served as a result.”\n",
       " “Today’s announcement should serve as a reminder that fraud related to medical products will not be tolerated,” \n",
       "said FDA Assistant Commissioner for Criminal Investigations Catherine A. Hermsen. “The FDA will continue to work \n",
       "with our law enforcement partners to bring to justice those who place profits above public health.”\n",
       " “Postal Inspectors worked closely with our partners at the U.S. Attorney’s Office, the FDA Office of Criminal \n",
       "Investigations, and the FBI to bring this case to court,” said USPIS San Francisco Division Acting Inspector in \n",
       "Charge Kevin Rho.\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Text: The FBI is committed to investigating corporate fraud and working with our partners to help keep our capital \n",
       "markets working effectively,” said FBI Special Agent in Charge Robert K. Tripp. “The FBI and our partners worked \n",
       "tirelessly on this multi-year case and are proud justice has been served as a result.”\n",
       " “Today’s announcement should serve as a reminder that fraud related to medical products will not be tolerated,” \n",
       "said FDA Assistant Commissioner for Criminal Investigations Catherine A. Hermsen. “The FDA will continue to work \n",
       "with our law enforcement partners to bring to justice those who place profits above public health.”\n",
       " “Postal Inspectors worked closely with our partners at the U.S. Attorney’s Office, the FDA Office of Criminal \n",
       "Investigations, and the FBI to bring this case to court,” said USPIS San Francisco Division Acting Inspector in \n",
       "Charge Kevin Rho.\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Source: \n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Source: \n",
       "\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred\u001b[0m\n",
       "\u001b[4;94ms\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Title: Northern District of California | Elizabeth Holmes Sentenced To More Than <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Title: Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[1;36m11\u001b[0m Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>. Similarity: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.6053</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "\u001b[1;36m3\u001b[0m. Similarity: \u001b[1;36m0.6053\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Text: The harsh ruling – which aligned with federal sentencing guidelines but was far more severe than the <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">18</span> \n",
       "months of house arrest requested by Holmes – sends a strong message from the US government to Silicon Valley, said \n",
       "Anat Alon-Beck, a law professor at Case Western Reserve University in Ohio.\n",
       "\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Text: The harsh ruling – which aligned with federal sentencing guidelines but was far more severe than the \u001b[1;36m18\u001b[0m \n",
       "months of house arrest requested by Holmes – sends a strong message from the US government to Silicon Valley, said \n",
       "Anat Alon-Beck, a law professor at Case Western Reserve University in Ohio.\n",
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Source: <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Source: \u001b[4;94mhttps://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Title: Theranos founder Elizabeth Holmes sentenced to more than <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> years for defrauding investors | Theranos | The \n",
       "Guardian\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Title: Theranos founder Elizabeth Holmes sentenced to more than \u001b[1;36m11\u001b[0m years for defrauding investors | Theranos | The \n",
       "Guardian\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">4</span>. Similarity: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5888</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "\u001b[1;36m4\u001b[0m. Similarity: \u001b[1;36m0.5888\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Text: U.S. District Court Judge Edward Davila, who presided over Holmes' trial, handed down the sentence.\n",
       "\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Text: U.S. District Court Judge Edward Davila, who presided over Holmes' trial, handed down the sentence.\n",
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Source: \n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.html</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Source: \n",
       "\u001b[4;94mhttps://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.html\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Title: Theranos founder Elizabeth Holmes sentenced to more than <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> years in prison\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Title: Theranos founder Elizabeth Holmes sentenced to more than \u001b[1;36m11\u001b[0m years in prison\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>. Similarity: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5769</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "\u001b[1;36m5\u001b[0m. Similarity: \u001b[1;36m0.5769\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Text: Assistant U.S. Attorneys Robert S. Leach, Jeff Schenk, John C. Bostic, and Kelly Volkar are prosecuting the \n",
       "case with the assistance of Madeline Wachs, Lakisha Holliman, Sara Slattery, Elise Etter, Susan Kreider, and Leeya \n",
       "Kekona. The prosecution is the result of an investigation by the FBI, USPIS, and the FDA Office of Criminal \n",
       "Investigations.\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Text: Assistant U.S. Attorneys Robert S. Leach, Jeff Schenk, John C. Bostic, and Kelly Volkar are prosecuting the \n",
       "case with the assistance of Madeline Wachs, Lakisha Holliman, Sara Slattery, Elise Etter, Susan Kreider, and Leeya \n",
       "Kekona. The prosecution is the result of an investigation by the FBI, USPIS, and the FDA Office of Criminal \n",
       "Investigations.\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Source: \n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Source: \n",
       "\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundred\u001b[0m\n",
       "\u001b[4;94ms\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Title: Northern District of California | Elizabeth Holmes Sentenced To More Than <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span> Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Title: Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[1;36m11\u001b[0m Years For Defrauding Theranos \n",
       "Investors Of Hundreds Of Millions | United States Department of Justice\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Perform semantic search using spaCy\n",
    "def semantic_search(query, chunks, nlp, similarity_threshold=0.5):\n",
    "    query_doc = nlp(query)\n",
    "    relevant_chunks = []\n",
    "    \n",
    "    for chunk in chunks:\n",
    "        chunk_doc = nlp(chunk['text'])\n",
    "        similarity = query_doc.similarity(chunk_doc)\n",
    "        \n",
    "        if similarity > similarity_threshold:\n",
    "            relevant_chunks.append((chunk, similarity))\n",
    "    \n",
    "    # Sort the relevant chunks by similarity score in descending order\n",
    "    relevant_chunks.sort(key=lambda x: x[1], reverse=True)\n",
    "    \n",
    "    return relevant_chunks\n",
    "\n",
    "# Perform the semantic search\n",
    "relevant_results = semantic_search(optimized_search_query, semantic_chunks, nlp)\n",
    "\n",
    "# Print the number of relevant chunks found\n",
    "console.print(f\"Found {len(relevant_results)} relevant chunks\")\n",
    "\n",
    "# Print the top 5 most relevant chunks (or all if less than 5)\n",
    "console.print(\"\\nTop relevant chunks:\")\n",
    "for i, (chunk, similarity) in enumerate(relevant_results[:5], 1):\n",
    "    console.print(f\"\\n{i}. Similarity: {similarity:.4f}\")\n",
    "    console.print(f\"Text: {chunk['text']}\")\n",
    "    console.print(f\"Source: {chunk['metadata']['source']}\")\n",
    "    console.print(f\"Title: {chunk['metadata']['title']}\")\n",
    "\n",
    "# Optionally, you can store these results for further processing\n",
    "# relevant_chunks = [chunk for chunk, _ in relevant_results]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Formatted chunks:\n",
       "</pre>\n"
      ],
      "text/plain": [
       "Formatted chunks:\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "    <span style=\"font-weight: bold\">&lt;</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff; font-weight: bold\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s-hundreds</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Northern District of California | Elizabeth Holmes Sentenced To More Than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> Years For Defrauding </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Theranos Investors Of Hundreds Of Millions | United States Department of Justice&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;Related Content</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Press Release</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">SAN JOSE – Elizabeth A. Holmes was sentenced today to </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">135</span><span style=\"color: #000000; text-decoration-color: #000000\"> months </span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">(</span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> years, </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span><span style=\"color: #000000; text-decoration-color: #000000\"> months</span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">)</span><span style=\"color: #000000; text-decoration-color: #000000\"> in federal prison for </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">defrauding investors in Theranos, Inc. of hundreds of millions of dollars, announced United States Attorney </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Stephanie M. Hinds, Federal Bureau of Investigation Special Agent in Charge Robert K. Tripp, Food and Drug </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Administration </span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">(</span><span style=\"color: #000000; text-decoration-color: #000000\">FDA</span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">)</span><span style=\"color: #000000; text-decoration-color: #000000\"> Assistant Commissioner for Criminal Investigations Catherine A. Hermsen, and U.S. Postal </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Inspection Service </span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">(</span><span style=\"color: #000000; text-decoration-color: #000000\">USPIS</span><span style=\"color: #000000; text-decoration-color: #000000; font-weight: bold\">)</span><span style=\"color: #000000; text-decoration-color: #000000\"> San Francisco Division Acting Inspector in Charge Kevin Rho. The sentence was handed </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">down by United States District Judge Edward J. Davila.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> “Silicon Valley has seen the rise of companies whose inventions have changed the world and, through intellectual </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">prowess, hard work, and sheer determination, this region continues to innovate,” said U.S. Attorney Stephanie M. </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Hinds.&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s-hundreds</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Northern District of California | Elizabeth Holmes Sentenced To More Than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> Years For Defrauding </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Theranos Investors Of Hundreds Of Millions | United States Department of Justice&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;The FBI is committed to investigating corporate fraud and working with our partners to help keep our </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">capital markets working effectively,” said FBI Special Agent in Charge Robert K. Tripp. “The FBI and our partners </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">worked tirelessly on this multi-year case and are proud justice has been served as a result.”</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> “Today’s announcement should serve as a reminder that fraud related to medical products will not be tolerated,” </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">said FDA Assistant Commissioner for Criminal Investigations Catherine A. Hermsen. “The FDA will continue to work </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">with our law enforcement partners to bring to justice those who place profits above public health.”</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> “Postal Inspectors worked closely with our partners at the U.S. Attorney’s Office, the FDA Office of Criminal </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Investigations, and the FBI to bring this case to court,” said USPIS San Francisco Division Acting Inspector in </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Charge Kevin Rho.&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Theranos founder Elizabeth Holmes sentenced to more than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> years for defrauding investors | Theranos | </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">The Guardian&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;The harsh ruling – which aligned with federal sentencing guidelines but was far more severe than the </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">18</span><span style=\"color: #000000; text-decoration-color: #000000\"> </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">months of house arrest requested by Holmes – sends a strong message from the US government to Silicon Valley, said </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Anat Alon-Beck, a law professor at Case Western Reserve University in Ohio.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-pr</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">ison.html</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Theranos founder Elizabeth Holmes sentenced to more than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> years in prison&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;U.S. District Court Judge Edward Davila, who presided over Holmes' trial, handed down the sentence.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s-hundreds</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Northern District of California | Elizabeth Holmes Sentenced To More Than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> Years For Defrauding </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Theranos Investors Of Hundreds Of Millions | United States Department of Justice&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;Assistant U.S. Attorneys Robert S. Leach, Jeff Schenk, John C. Bostic, and Kelly Volkar are prosecuting </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">the case with the assistance of Madeline Wachs, Lakisha Holliman, Sara Slattery, Elise Etter, Susan Kreider, and </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Leeya Kekona. The prosecution is the result of an investigation by the FBI, USPIS, and the FDA Office of Criminal </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Investigations.&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.bbc.com/news/business-58336998</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Theranos scandal: Who is Elizabeth Holmes and why was she on trial?&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;US Treasury Secretary George Schultz, media tycoon Rupert Murdoch and America's richest family, the </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Waltons, were among her backers.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor</span>\n",
       "<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">s-hundreds</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Northern District of California | Elizabeth Holmes Sentenced To More Than </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\"> Years For Defrauding </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Theranos Investors Of Hundreds Of Millions | United States Department of Justice&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;The New York Times Style Magazine. Holmes dined at the White House, joined the Board of Fellows of </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Harvard Medical School, and was named by Time as one of the </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">100</span><span style=\"color: #000000; text-decoration-color: #000000\"> Most Influential People in the World.&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;source&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;url&gt;</span><span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://www.npr.org/2023/05/30/1178728092/elizabeth-holmes-prison-sentence-theranos-fraud-silicon-valley</span><span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span>\n",
       "<span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">url</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;title&gt;Elizabeth Holmes has started her </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\">-year prison sentence. Here's what to know&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">title</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;text&gt;Elizabeth Holmes has started her </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\">-year prison sentence. Here's what to know</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">Disgraced Silicon Valley superstar Elizabeth Holmes has surrendered to federal prison in Texas to begin serving a </span>\n",
       "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">11</span><span style=\"color: #000000; text-decoration-color: #000000\">-year term for defrauding investors with her once high-flying blood-testing company Theranos.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> Holmes, a </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">39</span><span style=\"color: #000000; text-decoration-color: #000000\">-year-old mother of two, reported Tuesday to the prison camp in Bryan, Texas, an all-female facility </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">about </span><span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">100</span><span style=\"color: #000000; text-decoration-color: #000000\"> miles outside of Houston, where some family members of Holmes reside.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> Lawyers for Holmes attempted to delay the start of her prison sentence by asking that she remain free while she </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">appeals her conviction, but the 9th Circuit Court of Appeals denied her request, ruling that Holmes has not raised </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">a </span><span style=\"color: #008000; text-decoration-color: #008000\">\"substantial question\"</span><span style=\"color: #000000; text-decoration-color: #000000\"> of law or fact about her case.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\"> Here's what to know about the incarceration of Holmes, the most high-profile tech executive to be sentenced to </span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">prison time.</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">text</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">source</span><span style=\"font-weight: bold\">&gt;</span>\n",
       "    \n",
       "    \n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "    \u001b[1m<\u001b[0m\u001b[1;95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor\u001b[0m\n",
       "\u001b[4;94ms-hundreds\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m Years For Defrauding \u001b[0m\n",
       "\u001b[39mTheranos Investors Of Hundreds Of Millions | United States Department of Justice<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>Related Content\u001b[0m\n",
       "\u001b[39mPress Release\u001b[0m\n",
       "\u001b[39mSAN JOSE – Elizabeth A. Holmes was sentenced today to \u001b[0m\u001b[1;36m135\u001b[0m\u001b[39m months \u001b[0m\u001b[1;39m(\u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m years, \u001b[0m\u001b[1;36m3\u001b[0m\u001b[39m months\u001b[0m\u001b[1;39m)\u001b[0m\u001b[39m in federal prison for \u001b[0m\n",
       "\u001b[39mdefrauding investors in Theranos, Inc. of hundreds of millions of dollars, announced United States Attorney \u001b[0m\n",
       "\u001b[39mStephanie M. Hinds, Federal Bureau of Investigation Special Agent in Charge Robert K. Tripp, Food and Drug \u001b[0m\n",
       "\u001b[39mAdministration \u001b[0m\u001b[1;39m(\u001b[0m\u001b[39mFDA\u001b[0m\u001b[1;39m)\u001b[0m\u001b[39m Assistant Commissioner for Criminal Investigations Catherine A. Hermsen, and U.S. Postal \u001b[0m\n",
       "\u001b[39mInspection Service \u001b[0m\u001b[1;39m(\u001b[0m\u001b[39mUSPIS\u001b[0m\u001b[1;39m)\u001b[0m\u001b[39m San Francisco Division Acting Inspector in Charge Kevin Rho. The sentence was handed \u001b[0m\n",
       "\u001b[39mdown by United States District Judge Edward J. Davila.\u001b[0m\n",
       "\u001b[39m “Silicon Valley has seen the rise of companies whose inventions have changed the world and, through intellectual \u001b[0m\n",
       "\u001b[39mprowess, hard work, and sheer determination, this region continues to innovate,” said U.S. Attorney Stephanie M. \u001b[0m\n",
       "\u001b[39mHinds.<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor\u001b[0m\n",
       "\u001b[4;94ms-hundreds\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m Years For Defrauding \u001b[0m\n",
       "\u001b[39mTheranos Investors Of Hundreds Of Millions | United States Department of Justice<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>The FBI is committed to investigating corporate fraud and working with our partners to help keep our \u001b[0m\n",
       "\u001b[39mcapital markets working effectively,” said FBI Special Agent in Charge Robert K. Tripp. “The FBI and our partners \u001b[0m\n",
       "\u001b[39mworked tirelessly on this multi-year case and are proud justice has been served as a result.”\u001b[0m\n",
       "\u001b[39m “Today’s announcement should serve as a reminder that fraud related to medical products will not be tolerated,” \u001b[0m\n",
       "\u001b[39msaid FDA Assistant Commissioner for Criminal Investigations Catherine A. Hermsen. “The FDA will continue to work \u001b[0m\n",
       "\u001b[39mwith our law enforcement partners to bring to justice those who place profits above public health.”\u001b[0m\n",
       "\u001b[39m “Postal Inspectors worked closely with our partners at the U.S. Attorney’s Office, the FDA Office of Criminal \u001b[0m\n",
       "\u001b[39mInvestigations, and the FBI to bring this case to court,” said USPIS San Francisco Division Acting Inspector in \u001b[0m\n",
       "\u001b[39mCharge Kevin Rho.<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Theranos founder Elizabeth Holmes sentenced to more than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m years for defrauding investors | Theranos | \u001b[0m\n",
       "\u001b[39mThe Guardian<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>The harsh ruling – which aligned with federal sentencing guidelines but was far more severe than the \u001b[0m\u001b[1;36m18\u001b[0m\u001b[39m \u001b[0m\n",
       "\u001b[39mmonths of house arrest requested by Holmes – sends a strong message from the US government to Silicon Valley, said \u001b[0m\n",
       "\u001b[39mAnat Alon-Beck, a law professor at Case Western Reserve University in Ohio.\u001b[0m\n",
       "\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-pr\u001b[0m\n",
       "\u001b[4;94mison.html\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Theranos founder Elizabeth Holmes sentenced to more than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m years in prison<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>U.S. District Court Judge Edward Davila, who presided over Holmes' trial, handed down the sentence.\u001b[0m\n",
       "\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor\u001b[0m\n",
       "\u001b[4;94ms-hundreds\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m Years For Defrauding \u001b[0m\n",
       "\u001b[39mTheranos Investors Of Hundreds Of Millions | United States Department of Justice<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>Assistant U.S. Attorneys Robert S. Leach, Jeff Schenk, John C. Bostic, and Kelly Volkar are prosecuting \u001b[0m\n",
       "\u001b[39mthe case with the assistance of Madeline Wachs, Lakisha Holliman, Sara Slattery, Elise Etter, Susan Kreider, and \u001b[0m\n",
       "\u001b[39mLeeya Kekona. The prosecution is the result of an investigation by the FBI, USPIS, and the FDA Office of Criminal \u001b[0m\n",
       "\u001b[39mInvestigations.<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.bbc.com/news/business-58336998\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Theranos scandal: Who is Elizabeth Holmes and why was she on trial?<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>US Treasury Secretary George Schultz, media tycoon Rupert Murdoch and America's richest family, the \u001b[0m\n",
       "\u001b[39mWaltons, were among her backers.\u001b[0m\n",
       "\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investor\u001b[0m\n",
       "\u001b[4;94ms-hundreds\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Northern District of California | Elizabeth Holmes Sentenced To More Than \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m Years For Defrauding \u001b[0m\n",
       "\u001b[39mTheranos Investors Of Hundreds Of Millions | United States Department of Justice<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>The New York Times Style Magazine. Holmes dined at the White House, joined the Board of Fellows of \u001b[0m\n",
       "\u001b[39mHarvard Medical School, and was named by Time as one of the \u001b[0m\u001b[1;36m100\u001b[0m\u001b[39m Most Influential People in the World.<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    \u001b[0m\n",
       "\u001b[39m    <source>\u001b[0m\n",
       "\u001b[39m    <url>\u001b[0m\u001b[4;94mhttps://www.npr.org/2023/05/30/1178728092/elizabeth-holmes-prison-sentence-theranos-fraud-silicon-valley\u001b[0m\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\n",
       "\u001b[95murl\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <title>Elizabeth Holmes has started her \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m-year prison sentence. Here's what to know<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtitle\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <text>Elizabeth Holmes has started her \u001b[0m\u001b[1;36m11\u001b[0m\u001b[39m-year prison sentence. Here's what to know\u001b[0m\n",
       "\u001b[39mDisgraced Silicon Valley superstar Elizabeth Holmes has surrendered to federal prison in Texas to begin serving a \u001b[0m\n",
       "\u001b[1;36m11\u001b[0m\u001b[39m-year term for defrauding investors with her once high-flying blood-testing company Theranos.\u001b[0m\n",
       "\u001b[39m Holmes, a \u001b[0m\u001b[1;36m39\u001b[0m\u001b[39m-year-old mother of two, reported Tuesday to the prison camp in Bryan, Texas, an all-female facility \u001b[0m\n",
       "\u001b[39mabout \u001b[0m\u001b[1;36m100\u001b[0m\u001b[39m miles outside of Houston, where some family members of Holmes reside.\u001b[0m\n",
       "\u001b[39m Lawyers for Holmes attempted to delay the start of her prison sentence by asking that she remain free while she \u001b[0m\n",
       "\u001b[39mappeals her conviction, but the 9th Circuit Court of Appeals denied her request, ruling that Holmes has not raised \u001b[0m\n",
       "\u001b[39ma \u001b[0m\u001b[32m\"substantial question\"\u001b[0m\u001b[39m of law or fact about her case.\u001b[0m\n",
       "\u001b[39m Here's what to know about the incarceration of Holmes, the most high-profile tech executive to be sentenced to \u001b[0m\n",
       "\u001b[39mprison time.\u001b[0m\n",
       "\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95mtext\u001b[0m\u001b[39m>\u001b[0m\n",
       "\u001b[39m    <\u001b[0m\u001b[35m/\u001b[0m\u001b[95msource\u001b[0m\u001b[1m>\u001b[0m\n",
       "    \n",
       "    \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Initialize an empty string to store the formatted chunks\n",
    "formatted_chunks = \"\"\n",
    "\n",
    "# Iterate through the relevant chunks and format them\n",
    "for chunk, similarity in relevant_results:\n",
    "    formatted_chunk = f\"\"\"\n",
    "    <source>\n",
    "    <url>{chunk['metadata']['source']}</url>\n",
    "    <title>{chunk['metadata']['title']}</title>\n",
    "    <text>{chunk['text']}</text>\n",
    "    </source>\n",
    "    \n",
    "    \"\"\"\n",
    "    formatted_chunks += formatted_chunk\n",
    "\n",
    "# Print the formatted chunks string\n",
    "console.print(\"Formatted chunks:\")\n",
    "console.print(formatted_chunks)\n",
    "\n",
    "# Optionally, you can store this formatted_chunks string for further use\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = wr.get_rag_prompt_template().format(query=query, context=formatted_chunks)  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6960b578b16d43e286b6c98141b9cab8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮\n",
       "│                                                                                                                 │\n",
       "│                                           <span style=\"font-weight: bold; text-decoration: underline\">Is Elizabeth Holmes Guilty?</span>                                           │\n",
       "│                                                                                                                 │\n",
       "│ Yes, Elizabeth Holmes was found guilty of defrauding investors in her blood-testing startup, Theranos. She was  │\n",
       "│ sentenced to 135 months (11 years and 3 months) in federal prison for her actions, which involved misleading    │\n",
       "│ investors about the capabilities and performance of Theranos' blood-testing technology. This sentence was       │\n",
       "│ handed down by U.S. District Judge Edward J. Davila and reflects the severity of the fraud, which involved      │\n",
       "│ hundreds of millions of dollars.                                                                                │\n",
       "│                                                                                                                 │\n",
       "│ Holmes’ conviction serves as a significant legal precedent in the realm of corporate fraud, particularly in     │\n",
       "│ Silicon Valley, where the case has drawn considerable attention. The prosecution was a collaborative effort by  │\n",
       "│ the FBI, the U.S. Postal Inspection Service, and the FDA, emphasizing the seriousness with which such fraud is  │\n",
       "│ treated in the medical and corporate sectors.                                                                   │\n",
       "│                                                                                                                 │\n",
       "│                                                   <span style=\"font-weight: bold\">References</span>                                                    │\n",
       "│                                                                                                                 │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 1 </span><span style=\"font-weight: bold\">Northern District of California | Elizabeth Holmes Sentenced To More Than 11 Years For Defrauding Theranos </span>  │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">   </span><span style=\"font-weight: bold\">Investors Of Hundreds Of Millions</span>                                                                            │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">   </span>United States Department of Justice. <a href=\"https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundreds\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">Read more here</span></a>.                                                         │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 2 </span><span style=\"font-weight: bold\">Theranos founder Elizabeth Holmes sentenced to more than 11 years for defrauding investors</span>                   │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">   </span>The Guardian. <a href=\"https://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">Read more here</span></a>.                                                                                │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 3 </span><span style=\"font-weight: bold\">Theranos founder Elizabeth Holmes sentenced to more than 11 years in prison</span>                                  │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">   </span>CNBC. <a href=\"https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.html\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">Read more here</span></a>.                                                                                        │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 4 </span><span style=\"font-weight: bold\">Elizabeth Holmes has started her 11-year prison sentence. Here's what to know</span>                                │\n",
       "│ <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">   </span>NPR. <a href=\"https://www.npr.org/2023/05/30/1178728092/elizabeth-holmes-prison-sentence-theranos-fraud-silicon-valley\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">Read more here</span></a>.                                                                                         │\n",
       "╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
       "</pre>\n"
      ],
      "text/plain": [
       "╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮\n",
       "│                                                                                                                 │\n",
       "│                                           \u001b[1;4mIs Elizabeth Holmes Guilty?\u001b[0m                                           │\n",
       "│                                                                                                                 │\n",
       "│ Yes, Elizabeth Holmes was found guilty of defrauding investors in her blood-testing startup, Theranos. She was  │\n",
       "│ sentenced to 135 months (11 years and 3 months) in federal prison for her actions, which involved misleading    │\n",
       "│ investors about the capabilities and performance of Theranos' blood-testing technology. This sentence was       │\n",
       "│ handed down by U.S. District Judge Edward J. Davila and reflects the severity of the fraud, which involved      │\n",
       "│ hundreds of millions of dollars.                                                                                │\n",
       "│                                                                                                                 │\n",
       "│ Holmes’ conviction serves as a significant legal precedent in the realm of corporate fraud, particularly in     │\n",
       "│ Silicon Valley, where the case has drawn considerable attention. The prosecution was a collaborative effort by  │\n",
       "│ the FBI, the U.S. Postal Inspection Service, and the FDA, emphasizing the seriousness with which such fraud is  │\n",
       "│ treated in the medical and corporate sectors.                                                                   │\n",
       "│                                                                                                                 │\n",
       "│                                                   \u001b[1mReferences\u001b[0m                                                    │\n",
       "│                                                                                                                 │\n",
       "│ \u001b[1;33m 1 \u001b[0m\u001b[1mNorthern District of California | Elizabeth Holmes Sentenced To More Than 11 Years For Defrauding Theranos \u001b[0m  │\n",
       "│ \u001b[1;33m   \u001b[0m\u001b[1mInvestors Of Hundreds Of Millions\u001b[0m                                                                            │\n",
       "│ \u001b[1;33m   \u001b[0mUnited States Department of Justice. \u001b]8;id=534523;https://www.justice.gov/usao-ndca/pr/elizabeth-holmes-sentenced-more-11-years-defrauding-theranos-investors-hundreds\u001b\\\u001b[4;34mRead more here\u001b[0m\u001b]8;;\u001b\\.                                                         │\n",
       "│ \u001b[1;33m 2 \u001b[0m\u001b[1mTheranos founder Elizabeth Holmes sentenced to more than 11 years for defrauding investors\u001b[0m                   │\n",
       "│ \u001b[1;33m   \u001b[0mThe Guardian. \u001b]8;id=993177;https://www.theguardian.com/us-news/2022/nov/18/elizabeth-holmes-theranos-trial-sentencing\u001b\\\u001b[4;34mRead more here\u001b[0m\u001b]8;;\u001b\\.                                                                                │\n",
       "│ \u001b[1;33m 3 \u001b[0m\u001b[1mTheranos founder Elizabeth Holmes sentenced to more than 11 years in prison\u001b[0m                                  │\n",
       "│ \u001b[1;33m   \u001b[0mCNBC. \u001b]8;id=246555;https://www.cnbc.com/2022/11/18/former-theranos-ceo-elizabeth-holmes-sentenced-to-more-than-11-years-in-prison.html\u001b\\\u001b[4;34mRead more here\u001b[0m\u001b]8;;\u001b\\.                                                                                        │\n",
       "│ \u001b[1;33m 4 \u001b[0m\u001b[1mElizabeth Holmes has started her 11-year prison sentence. Here's what to know\u001b[0m                                │\n",
       "│ \u001b[1;33m   \u001b[0mNPR. \u001b]8;id=513361;https://www.npr.org/2023/05/30/1178728092/elizabeth-holmes-prison-sentence-theranos-fraud-silicon-valley\u001b\\\u001b[4;34mRead more here\u001b[0m\u001b]8;;\u001b\\.                                                                                         │\n",
       "╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\n"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from rich.live import Live\n",
    "from rich.markdown import Markdown\n",
    "from rich.panel import Panel\n",
    "\n",
    "panel = Panel(\"AI response\")\n",
    "\n",
    "with Live(panel, auto_refresh=True) as live:\n",
    "    full_response = \"\"\n",
    "    for chunk in chat.stream(prompt):\n",
    "        full_response += chunk.content\n",
    "        panel.fit(Markdown(full_response))\n",
    "\n",
    "panel.fit(Markdown(full_response))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "                                       <span style=\"font-weight: bold; text-decoration: underline\">Different Funding Stages of a Startup</span>                                       \n",
       "\n",
       "Startups typically progress through several distinct funding stages, each with its own characteristics, goals, and \n",
       "challenges. Understanding these stages is crucial for entrepreneurs seeking to navigate the startup landscape      \n",
       "effectively. Here’s an overview of the primary funding stages:                                                     \n",
       "\n",
       "                                                 <span style=\"font-weight: bold\">1. Pre-Seed Stage</span>                                                 \n",
       "\n",
       "The pre-seed stage is the earliest phase of funding. At this point, entrepreneurs often use their own resources to \n",
       "develop their ideas. The primary goal is to assemble a team and create a minimum viable product (MVP) to showcase  \n",
       "potential to attract further investment. This stage is crucial for validating the business concept and assessing   \n",
       "its viability.                                                                                                     \n",
       "\n",
       "                                                   <span style=\"font-weight: bold\">2. Seed Stage</span>                                                   \n",
       "\n",
       "Seed funding is the first official equity funding stage, where startups raise capital in exchange for equity       \n",
       "ownership. This funding typically ranges from a few thousand dollars to several million. The focus during this     \n",
       "stage is on product development and market research, as the startup aims to validate its business model and gather \n",
       "initial customer feedback. Approximately 29% of startups fail due to a lack of capital at this stage, highlighting \n",
       "its importance.                                                                                                    \n",
       "\n",
       "                                                 <span style=\"font-weight: bold\">3. Series A Stage</span>                                                 \n",
       "\n",
       "In the Series A stage, startups seek venture capital funding to scale their operations. By this time, they should  \n",
       "have a developed product and a consistent revenue stream. The typical amount raised in a Series A round ranges from\n",
       "$1 million to $15 million, with an average of around $13 million. The goal here is to optimize the product and     \n",
       "expand the customer base.                                                                                          \n",
       "\n",
       "                                                 <span style=\"font-weight: bold\">4. Series B Stage</span>                                                 \n",
       "\n",
       "Series B funding is for startups that have established a substantial user base and are looking to expand further.  \n",
       "This round often involves larger investments from venture capitalists who want to play a more significant role in  \n",
       "the company's strategy. The funds are typically used to scale operations and increase market reach.                \n",
       "\n",
       "                                              <span style=\"font-weight: bold\">5. Series C and Beyond</span>                                               \n",
       "\n",
       "Startups that have met their goals in previous stages may seek Series C funding or further rounds (Series D, etc.) \n",
       "to continue expanding or to prepare for an Initial Public Offering (IPO). This stage allows startups to solidify   \n",
       "their market position and reach additional growth milestones.                                                      \n",
       "\n",
       "                                         <span style=\"font-weight: bold\">6. IPO (Initial Public Offering)</span>                                          \n",
       "\n",
       "An IPO is the process through which a startup offers its shares to the public for the first time. This stage is    \n",
       "critical for providing liquidity for investors and raising significant capital to fuel further growth. The         \n",
       "valuation at this stage is crucial, as it determines the stock price and overall market perception of the startup. \n",
       "\n",
       "Each of these stages presents unique challenges and opportunities, and the successful navigation through them is   \n",
       "essential for the growth and sustainability of a startup.                                                          \n",
       "\n",
       "\n",
       "                                                    <span style=\"font-weight: bold; text-decoration: underline\">References</span>                                                     \n",
       "\n",
       "<span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> • </span><a href=\"https://stripe.com/resources/more/what-are-the-stages-of-a-startup\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">What are the startup funding stages? | Stripe</span></a>                                                                   \n",
       "<span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> • </span><a href=\"https://www.startups.com/library/expert-advice/different-stages-of-funding-for-startups\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">A Guide to Different Stages of Funding for Startups</span></a>                                                             \n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n",
       "                                       \u001b[1;4mDifferent Funding Stages of a Startup\u001b[0m                                       \n",
       "\n",
       "Startups typically progress through several distinct funding stages, each with its own characteristics, goals, and \n",
       "challenges. Understanding these stages is crucial for entrepreneurs seeking to navigate the startup landscape      \n",
       "effectively. Here’s an overview of the primary funding stages:                                                     \n",
       "\n",
       "                                                 \u001b[1m1. Pre-Seed Stage\u001b[0m                                                 \n",
       "\n",
       "The pre-seed stage is the earliest phase of funding. At this point, entrepreneurs often use their own resources to \n",
       "develop their ideas. The primary goal is to assemble a team and create a minimum viable product (MVP) to showcase  \n",
       "potential to attract further investment. This stage is crucial for validating the business concept and assessing   \n",
       "its viability.                                                                                                     \n",
       "\n",
       "                                                   \u001b[1m2. Seed Stage\u001b[0m                                                   \n",
       "\n",
       "Seed funding is the first official equity funding stage, where startups raise capital in exchange for equity       \n",
       "ownership. This funding typically ranges from a few thousand dollars to several million. The focus during this     \n",
       "stage is on product development and market research, as the startup aims to validate its business model and gather \n",
       "initial customer feedback. Approximately 29% of startups fail due to a lack of capital at this stage, highlighting \n",
       "its importance.                                                                                                    \n",
       "\n",
       "                                                 \u001b[1m3. Series A Stage\u001b[0m                                                 \n",
       "\n",
       "In the Series A stage, startups seek venture capital funding to scale their operations. By this time, they should  \n",
       "have a developed product and a consistent revenue stream. The typical amount raised in a Series A round ranges from\n",
       "$1 million to $15 million, with an average of around $13 million. The goal here is to optimize the product and     \n",
       "expand the customer base.                                                                                          \n",
       "\n",
       "                                                 \u001b[1m4. Series B Stage\u001b[0m                                                 \n",
       "\n",
       "Series B funding is for startups that have established a substantial user base and are looking to expand further.  \n",
       "This round often involves larger investments from venture capitalists who want to play a more significant role in  \n",
       "the company's strategy. The funds are typically used to scale operations and increase market reach.                \n",
       "\n",
       "                                              \u001b[1m5. Series C and Beyond\u001b[0m                                               \n",
       "\n",
       "Startups that have met their goals in previous stages may seek Series C funding or further rounds (Series D, etc.) \n",
       "to continue expanding or to prepare for an Initial Public Offering (IPO). This stage allows startups to solidify   \n",
       "their market position and reach additional growth milestones.                                                      \n",
       "\n",
       "                                         \u001b[1m6. IPO (Initial Public Offering)\u001b[0m                                          \n",
       "\n",
       "An IPO is the process through which a startup offers its shares to the public for the first time. This stage is    \n",
       "critical for providing liquidity for investors and raising significant capital to fuel further growth. The         \n",
       "valuation at this stage is crucial, as it determines the stock price and overall market perception of the startup. \n",
       "\n",
       "Each of these stages presents unique challenges and opportunities, and the successful navigation through them is   \n",
       "essential for the growth and sustainability of a startup.                                                          \n",
       "\n",
       "\n",
       "                                                    \u001b[1;4mReferences\u001b[0m                                                     \n",
       "\n",
       "\u001b[1;33m • \u001b[0m\u001b]8;id=999288;https://stripe.com/resources/more/what-are-the-stages-of-a-startup\u001b\\\u001b[4;34mWhat are the startup funding stages? | Stripe\u001b[0m\u001b]8;;\u001b\\                                                                   \n",
       "\u001b[1;33m • \u001b[0m\u001b]8;id=935378;https://www.startups.com/library/expert-advice/different-stages-of-funding-for-startups\u001b\\\u001b[4;34mA Guide to Different Stages of Funding for Startups\u001b[0m\u001b]8;;\u001b\\                                                             \n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "full_response = chat.invoke(prompt).content\n",
    "console.print(Markdown(full_response))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}