{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5",
   "metadata": {},
   "source": [
    "# Week 1 Exercise | Study Guide Generation with Llama 3.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c1070317-3ed9-4659-abe3-828943230e03",
   "metadata": {
    "editable": false,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "import json\n",
    "import re\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display, update_display\n",
    "from openai import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4a456906-915a-4bfd-bb9d-57e505c5093f",
   "metadata": {},
   "outputs": [],
   "source": [
    "openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
    "MODEL = 'llama3.2'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5cd638a2-ab65-41cf-97bb-673c3ec117c4",
   "metadata": {},
   "source": [
    "### 1. Web Scraper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "504f3bce-f922-46a9-844a-b13d47507b8a",
   "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",
    "        self.url = url\n",
    "        response = requests.get(url, headers=headers)\n",
    "        self.body = response.content\n",
    "        soup = BeautifulSoup(self.body, 'html.parser')\n",
    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
    "        if soup.body:\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",
    "        else:\n",
    "            self.text = \"\"\n",
    "        links = [link.get('href') for link in soup.find_all('a')]\n",
    "        self.links = [link for link in links if link]\n",
    "\n",
    "    def get_contents(self):\n",
    "        return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2bbf43c5-774d-4d4e-91ff-772781fdfeaf",
   "metadata": {},
   "source": [
    "### 2. Curriculum Extraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3f0d0137-52b0-47a8-81a8-11a90a010798",
   "metadata": {},
   "outputs": [],
   "source": [
    "curriculum_system_prompt = \"\"\"You are provided with the text content of a webpage. \n",
    "Your task is to design a student-friendly curriculum from this content. \n",
    "Break down the material into clear modules or lessons, each with a title and a short description. \n",
    "Focus on organizing the information in a logical order, as if preparing a study plan.\n",
    "\n",
    "You should respond in JSON as in this example:\n",
    "{\n",
    "    \"curriculum\": [\n",
    "        {\n",
    "            \"module\": \"Introduction to Machine Learning\",\n",
    "            \"description\": \"Basic concepts and history of machine learning, why it matters, and common applications.\"\n",
    "        },\n",
    "        {\n",
    "            \"module\": \"Supervised Learning\",\n",
    "            \"description\": \"Learn about labeled data, classification, and regression methods.\"\n",
    "        },\n",
    "        {\n",
    "            \"module\": \"Unsupervised Learning\",\n",
    "            \"description\": \"Understand clustering, dimensionality reduction, and when to use unsupervised approaches.\"\n",
    "        }\n",
    "    ]\n",
    "}\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d89a0be8-0254-43b5-ab9a-6224069a1246",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_curriculum_user_prompt(website):\n",
    "    user_prompt = f\"Here is the text content of the website at {website.url}:\\n\\n\"\n",
    "    user_prompt += website.text\n",
    "    user_prompt += \"\\n\\nPlease create a student-friendly curriculum from this content. \"\n",
    "    user_prompt += \"Break it down into clear modules or lessons, each with a title and a short description. \"\n",
    "    user_prompt += \"Return your response in JSON format\"\n",
    "    return user_prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da74104c-81a3-4d12-a377-e202ddfe57bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_curriculum(website):\n",
    "    stream = openai.chat.completions.create(\n",
    "        model=MODEL,\n",
    "        messages=[\n",
    "            {\"role\": \"system\", \"content\": curriculum_system_prompt},\n",
    "            {\"role\": \"user\", \"content\": get_curriculum_user_prompt(website)}\n",
    "        ],\n",
    "        stream=True\n",
    "    )\n",
    "    response_text = \"\"\n",
    "    display_handle = display(Markdown(\"\"), display_id=True)\n",
    "    for chunk in stream:\n",
    "        delta = chunk.choices[0].delta.content or ''\n",
    "        response_text += delta\n",
    "        update_display(Markdown(response_text), display_id=display_handle.display_id)\n",
    "    try:\n",
    "        json_text = re.search(r\"\\{.*\\}\", response_text, re.DOTALL).group()\n",
    "        curriculum_json = json.loads(json_text)\n",
    "    except Exception as e:\n",
    "        print(\"Failed to parse JSON:\", e)\n",
    "        curriculum_json = {\"error\": \"JSON parse failed\", \"raw\": response_text}\n",
    "\n",
    "    return curriculum_json"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df68eafc-e529-400c-a61b-0140c38909a3",
   "metadata": {},
   "source": [
    "### 3. Study Guide"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b3db9d4-5edd-4a0c-8d5c-45ea455d8eb0",
   "metadata": {},
   "outputs": [],
   "source": [
    "guide_system_prompt = \"\"\"You are an educational assistant. \n",
    "You are given a curriculum JSON with modules and descriptions.\n",
    "Your task is to create a student-friendly study guide based on this curriculum.\n",
    "- Organize the guide step by step, with clear headings, tips, and examples where appropriate.\n",
    "- Make it engaging and easy to follow.\n",
    "- Adapt the content according to the student's level, language, and tone.\n",
    "- Always respond in markdown format suitable for a student guide.\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "16f85360-6f06-4bb3-878a-5f3b8d8f20d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_study_guide_user_prompt(curriculum_json, student_level=\"beginner\", language=\"English\", tone=\"friendly\"):\n",
    "    return f\"\"\"\n",
    "            Student Level: {student_level}\n",
    "            Language: {language}\n",
    "            Tone: {tone}\n",
    "            \n",
    "            Here is the curriculum JSON:\n",
    "            \n",
    "            {json.dumps(curriculum_json, indent=2)}\n",
    "            \n",
    "            Please convert it into a study guide for the student.\n",
    "            \"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bc9b949d-df2b-475c-9a84-597a47ed6e85",
   "metadata": {},
   "outputs": [],
   "source": [
    "def stream_study_guide(curriculum_json, student_level=\"beginner\", language=\"English\", tone=\"friendly\"):\n",
    "    \n",
    "    user_prompt = get_study_guide_user_prompt(curriculum_json, student_level, language, tone)\n",
    "    stream = openai.chat.completions.create(\n",
    "        model=MODEL,\n",
    "        messages=[\n",
    "            {\"role\": \"system\", \"content\": guide_system_prompt},\n",
    "            {\"role\": \"user\", \"content\": user_prompt}\n",
    "        ],\n",
    "        stream=True\n",
    "    )\n",
    "\n",
    "    response_text = \"\"\n",
    "    display_handle = display(Markdown(\"\"), display_id=True)\n",
    "    for chunk in stream:\n",
    "        delta = chunk.choices[0].delta.content or ''\n",
    "        response_text += delta\n",
    "        update_display(Markdown(response_text), display_id=display_handle.display_id)\n",
    "    \n",
    "    return response_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8c289b7c-c991-45b5-adc3-7468af393e50",
   "metadata": {},
   "outputs": [],
   "source": [
    "page = Website(\"https://en.wikipedia.org/wiki/Rock_and_roll\")\n",
    "curriculum_json = get_curriculum(page)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c697d63-2230-4e04-a28b-c0e8fc85753e",
   "metadata": {},
   "outputs": [],
   "source": [
    "study_guide_text = stream_study_guide(\n",
    "    curriculum_json,\n",
    "    student_level=\"beginner\",\n",
    "    language=\"English\",\n",
    "    tone=\"friendly\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c0960f87-fd29-4ae3-8405-f4fde1f50f89",
   "metadata": {},
   "outputs": [],
   "source": [
    "study_guide_text = stream_study_guide(\n",
    "    curriculum_json,\n",
    "    student_level=\"advanced\",\n",
    "    language=\"English\",\n",
    "    tone=\"professional, detailed\"\n",
    ")"
   ]
  }
 ],
 "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
}