{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7317c777-7a59-4719-842f-b3018aa7e73f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display\n",
    "import ollama"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "26b1489d-c043-4631-872b-e1e28fec9eed",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Constants\n",
    "\n",
    "MODEL = \"llama3.2\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a5630e12-40f5-40ea-996b-4b1a5d9c8697",
   "metadata": {},
   "outputs": [],
   "source": [
    "# A class to represent a Webpage\n",
    "\n",
    "class Website:\n",
    "    \"\"\"\n",
    "    A utility class to represent a Website that we have scraped\n",
    "    \"\"\"\n",
    "    url: str\n",
    "    title: str\n",
    "    text: str\n",
    "\n",
    "    def __init__(self, url):\n",
    "        \"\"\"\n",
    "        Create this Website object from the given url using the BeautifulSoup library\n",
    "        \"\"\"\n",
    "        self.url = url\n",
    "        response = requests.get(url)\n",
    "        soup = BeautifulSoup(response.content, 'html.parser')\n",
    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
    "        for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
    "            irrelevant.decompose()\n",
    "        self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "510e0447-ed82-4337-b0aa-f9752b41711a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n",
    "\n",
    "system_prompt = \"You are an assistant that analyzes the contents of a website \\\n",
    "and provides a short summary, ignoring text that might be navigation related. \\\n",
    "Respond in markdown.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7a0926ae-8580-4f0a-8935-ce390b926074",
   "metadata": {},
   "outputs": [],
   "source": [
    "# A function that writes a User Prompt that asks for summaries of websites:\n",
    "\n",
    "def user_prompt_for(website):\n",
    "    user_prompt = f\"You are looking at a website titled {website.title}\"\n",
    "    user_prompt += \"The contents of this website is as follows; \\\n",
    "please provide a short summary of this website in markdown. \\\n",
    "If it includes news or announcements, then summarize these too.\\n\\n\"\n",
    "    user_prompt += website.text\n",
    "    return user_prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "963edaa9-daba-4fa1-8db6-518f22261ab0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# See how this function creates exactly the format above\n",
    "\n",
    "def messages_for(website):\n",
    "    return [\n",
    "        {\"role\": \"system\", \"content\": system_prompt},\n",
    "        {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
    "    ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "04c7a991-df38-4e73-8015-73684bdd7810",
   "metadata": {},
   "outputs": [],
   "source": [
    "# And now: call the Ollama function \n",
    "\n",
    "def summarize(url):\n",
    "    website = Website(url)\n",
    "    messages = messages_for(website)\n",
    "    response = ollama.chat(model=MODEL, messages=messages)\n",
    "    return response['message']['content']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b08efad7-7dbe-438e-898a-fc7ae7395149",
   "metadata": {},
   "outputs": [],
   "source": [
    "summarize(\"https://www.allrecipes.com/recipes/14485/healthy-recipes/main-dishes/chicken/\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6ec180e8-4e2a-4e02-afc6-39a90a87bd7e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# A function to display this nicely in the Jupyter output, using markdown\n",
    "\n",
    "def display_summary(url):\n",
    "    summary = summarize(url)\n",
    "    display(Markdown(summary))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "967b874a-af3a-494a-bb02-c83232d0f9a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "display_summary(\"https://www.allrecipes.com/recipes/14485/healthy-recipes/main-dishes/chicken/\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1148b8d0-1e44-4ea1-ba1f-44eb25e0af18",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}