LLM_Engineering_OLD/week1/community-contributions/day2_exercise_llama3.2.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "786b2ed1-f82e-4ca4-8113-c4515b36e970",
   "metadata": {},
   "source": [
    "# Day 2 Exercise | Website Summarizer with Llama 3.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b88bf233-29e0-4c01-a4da-8a16896a95e3",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f66f620e-ebf6-45d3-a710-2bb931cac841",
   "metadata": {},
   "source": [
    "### 1. Scraping info from website:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4e300303-02ac-4d60-9c8c-044a4627be9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "137714b9-24eb-4541-8f24-507dbcd09279",
   "metadata": {},
   "outputs": [],
   "source": [
    "ed = Website(\"https://edwarddonner.com\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "77ba1b4b-fc4c-4e3c-bef7-c4d4281d8263",
   "metadata": {},
   "source": [
    "### 2. Ollama configuration:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "97811fcb-1ceb-49a8-bfb9-2e610605c406",
   "metadata": {},
   "outputs": [],
   "source": [
    "OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
    "HEADERS = {\"Content-Type\": \"application/json\"}\n",
    "MODEL = \"llama3.2\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "392326b8-ad0f-4bc9-b055-6220f8bcc57c",
   "metadata": {},
   "outputs": [],
   "source": [
    "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",
    "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",
    "user_prompt = user_prompt_for(ed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8caa94ff-5ace-4f9b-b2f0-beb6ff550636",
   "metadata": {},
   "outputs": [],
   "source": [
    "messages = [\n",
    "    {\"role\": \"system\", \"content\": system_prompt},\n",
    "    {\"role\": \"user\", \"content\": user_prompt}\n",
    "]\n",
    "\n",
    "payload = {\n",
    "        \"model\": MODEL,\n",
    "        \"messages\": messages,\n",
    "        \"stream\": False\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f5f856bc-0437-4607-9204-5390d2dfd8db",
   "metadata": {},
   "source": [
    "### 3. Get & display summary:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a7fd6f93-92ae-419f-b8b6-ee8214e0d93f",
   "metadata": {},
   "outputs": [],
   "source": [
    "response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n",
    "summary = response.json()['message']['content']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "78e4a433-b974-463f-82d0-b4696c63e0ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "def display_summary(summary_text: str):\n",
    "    cleaned = summary_text.encode('utf-8').decode('unicode_escape')\n",
    "    cleaned = cleaned.strip()\n",
    "    display(Markdown(cleaned))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dc408f1d-fe26-4bd6-859f-d18118f74ca6",
   "metadata": {},
   "outputs": [],
   "source": [
    "display_summary(summary)"
   ]
  }
 ],
 "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
}