LLM_Engineering_OLD/week1/community-contributions/day2_Ollama_Solution.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "663695bd-d1f2-4acf-8669-02d9f75f1bf4",
   "metadata": {},
   "source": [
    "# Day 2: Ollama Solution for Website Summarization\n",
    "### Building and Deploying Website Summarization Tools with Ollama"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "112ef04a-136e-4e65-b94e-8674a64606ed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "**Summary of Website**\n",
       "=========================\n",
       "### Overview\n",
       "\n",
       "The \"Home - Edward Donner\" website is a personal blog hosted by Edward Donner, the co-founder and CTO of Nebula.io. The website shares insights on his professional experiences with AI, particularly in applying LLMs (Large Language Models) to help people discover their potential.\n",
       "\n",
       "### Recent Developments\n",
       "------------------------\n",
       "\n",
       "* **Courses**: Upcoming online courses, including \"Connecting my courses – become an LLM expert and leader\" and \"The Complete Agentic AI Engineering Course\"\n",
       "* **Events**:\n",
       "\t+ May 28, 2025: Launch connecting his courses (LLM Expert and Leader)\n",
       "\t+ May 18, 2025: 2025 AI Executive Briefing\n",
       "\t+ April 21, 2025: AI Executive Briefing\n",
       "\t+ January 23, 2025: The Complete Agentic AI Engineering Course\n",
       "\n",
       "### About the Creator\n",
       "-------------------------\n",
       "\n",
       "* Edward Donner is the co-founder and CTO of Nebula.io.\n",
       "* He has experience as a founder and CEO of an AI startup that was acquired in 2021.\n",
       "* His interests include DJing, amateur electronic music production, and reading Hacker News.\n",
       "\n",
       "### Contact Information\n",
       "-------------------------\n",
       "\n",
       "* Email: [ed @ edwarddonner . com](mailto:ed@edwarddonner.com)\n",
       "* Website: www.edwarddonner.com\n",
       "* Social media links:\n",
       "\t+ LinkedIn\n",
       "\t+ Twitter\n",
       "\t+ Facebook"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display\n",
    "\n",
    "OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
    "HEADERS = {\"Content-Type\": \"application/json\"}\n",
    "MODEL = \"llama3.2\"\n",
    "\n",
    "headers = {\n",
    " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
    "}\n",
    "\n",
    "class Website:\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, headers=headers)\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)\n",
    "\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.\"\n",
    "\n",
    "def user_prompt_for(website):\n",
    "    user_prompt = f\"You are looking at a website titled {website.title}\"\n",
    "    user_prompt += \"\\nThe 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\n",
    "\n",
    "def messages_for(website):\n",
    "    return [\n",
    "        {\"role\": \"system\", \"content\": system_prompt},\n",
    "        {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
    "    ]\n",
    "\n",
    "url = \"https://sitemakerlab.com/\" \n",
    "site = Website(url)\n",
    "messages = messages_for(site)\n",
    "\n",
    "def summarize(url):\n",
    "    website = Website(url)\n",
    "    response = ollama_via_openai.chat.completions.create(\n",
    "        model = MODEL,\n",
    "        messages = messages_for(website)\n",
    "    )\n",
    "    return response.choices[0].message.content\n",
    "\n",
    "def display_summary(url):\n",
    "    summary = summarize(url)\n",
    "    display(Markdown(summary))\n",
    "\n",
    "display_summary(\"https://edwarddonner.com\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "566373e7-8612-4c39-a432-7795cb7d2e6c",
   "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
}