LLM_Engineering_OLD/week1/community-contributions/day2 EXERCISE-Summarization-Ollama.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e3ce0a59-fbfb-4377-85db-f62f95039200",
   "metadata": {},
   "source": [
    "# Day2 EXERCISE - Summarization using Ollama"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "from dotenv import load_dotenv\n",
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "29ddd15d-a3c5-4f4e-a678-873f56162724",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Constants\n",
    "\n",
    "OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
    "HEADERS = {\"Content-Type\": \"application/json\"}\n",
    "MODEL = \"llama3.2\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cb5c0f84-4e4d-4f87-b492-e09d0333a638",
   "metadata": {},
   "outputs": [],
   "source": [
    "# A class to represent a Webpage\n",
    "# If you're not familiar with Classes, check out the \"Intermediate Python\" notebook\n",
    "\n",
    "# Some websites need you to use proper headers when fetching them:\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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "23457b52-c85b-4dc1-b946-6f1461dc0675",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "ed = Website(\"https://edwarddonner.com\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bed206ed-43c1-4f68-ad01-a738b3b4648d",
   "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": "e558f381-614a-461f-83bc-e5bdc99460df",
   "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 += \"\\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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e5ba638d-aeb9-441e-a62a-8e8027ad8439",
   "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": "e85ca2ec-3e46-4b8f-9c2f-66e7d20138fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "#website search\n",
    "\n",
    "ed = Website(\"https://edwarddonner.com\")\n",
    "messages=messages_for(ed)\n",
    "\n",
    "payload = {\n",
    "        \"model\": MODEL,\n",
    "        \"messages\": messages,\n",
    "        \"stream\": False\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7745b9c4-57dc-4867-9180-61fa5db55eb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import ollama\n",
    "\n",
    "response = ollama.chat(model=MODEL, messages=messages)\n",
    "print(response['message']['content'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "402d5686-4e76-4110-b65a-b3906c35c0a4",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}