{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5",
   "metadata": {},
   "source": [
    "# End of week 1 exercise\n",
    "\n",
    "To demonstrate your familiarity with OpenAI API, and also Ollama, build a tool that takes a technical question,  \n",
    "and responds with an explanation. This is a tool that you will be able to use yourself during the course!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c1070317-3ed9-4659-abe3-828943230e03",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import os, re, requests, json, ollama\n",
    "from typing import List\n",
    "from dotenv import load_dotenv\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": [
    "# constants\n",
    "\n",
    "MODEL_GPT = 'gpt-4o-mini'\n",
    "MODEL_LLAMA = 'llama3.2'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a8d7923c-5f28-4c30-8556-342d7c8497c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up environment\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",
    "openai = OpenAI()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3f0d0137-52b0-47a8-81a8-11a90a010798",
   "metadata": {},
   "outputs": [],
   "source": [
    "# here is the question; type over this to ask something new\n",
    "\n",
    "# question = \"\"\"\n",
    "# Please explain what this code does and why:\n",
    "# yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n",
    "# \"\"\"\n",
    "\n",
    "question = \"\"\"\n",
    "How good at Software Development is Elijah Rwothoromo? \\\n",
    "He has a Wordpress site https://rwothoromo.wordpress.com/. \\\n",
    "He also has a LinkedIn profile https://www.linkedin.com/in/rwothoromoelaijah/. \\\n",
    "What can we learn from him?\n",
    "\"\"\"\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e14fd3a1-0aca-4794-a0e0-57458e111fc9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Process URLs in the question to improve the prompt\n",
    "\n",
    "# Extract all URLs from the question string using regular expressions\n",
    "urls = re.findall(r'https?://[^\\s)]+', question)\n",
    "\n",
    "# Fetch the content for each URL using the Website class\n",
    "scraped_content = []\n",
    "for url in urls:\n",
    "    print(f\"Scraping: {url}\")\n",
    "    try:\n",
    "        site = Website(url)\n",
    "        content = f\"Content from {url}:\\n---\\n{site.text}\\n---\\n\" # delimiter ---\n",
    "        scraped_content.append(content)\n",
    "    except Exception as e:\n",
    "        print(f\"Could not scrape {url}: {e}\")\n",
    "        scraped_content.append(f\"Could not retrieve content from {url}.\\n\")\n",
    "\n",
    "# Combine all the scraped text into one string\n",
    "all_scraped_text = \"\\n\".join(scraped_content)\n",
    "\n",
    "# Update the question with the scraped content\n",
    "augmented_question = f\"\"\"\n",
    "Based on the following information, please answer the user's original question.\n",
    "\n",
    "--- TEXT FROM WEBSITES ---\n",
    "{all_scraped_text}\n",
    "--- END TEXT FROM WEBSITES ---\n",
    "\n",
    "--- ORIGINAL QUESTION ---\n",
    "{question}\n",
    "\"\"\"\n",
    "\n",
    "# system prompt to be more accurate for AI to just analyze the provided text.\n",
    "system_prompt = \"You are an expert assistant. \\\n",
    "Analyze the user's question and the provided text from relevant websites to synthesize a comprehensive answer in markdown format.\\\n",
    "Provides a short summary, ignoring text that might be navigation-related.\"\n",
    "\n",
    "# Create the messages list with the new augmented prompt\n",
    "messages = [\n",
    "    {\"role\": \"system\", \"content\": system_prompt},\n",
    "    {\"role\": \"user\", \"content\": augmented_question},\n",
    "]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "60ce7000-a4a5-4cce-a261-e75ef45063b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get gpt-4o-mini to answer, with streaming\n",
    "\n",
    "def get_gpt_response(question):\n",
    "    # return response.choices[0].message.content\n",
    "\n",
    "    stream = openai.chat.completions.create(\n",
    "        model=MODEL_GPT,\n",
    "        messages=messages,\n",
    "        stream=True\n",
    "    )\n",
    "    \n",
    "    response = \"\"\n",
    "    display_handle = display(Markdown(\"\"), display_id=True)\n",
    "    for chunk in stream:\n",
    "        response += chunk.choices[0].delta.content or ''\n",
    "        response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
    "        update_display(Markdown(response), display_id=display_handle.display_id)\n",
    "\n",
    "get_gpt_response(question)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get Llama 3.2 to answer\n",
    "def get_llama_response(question):\n",
    "    response = ollama.chat(\n",
    "        model=MODEL_LLAMA,\n",
    "        messages=messages,\n",
    "        stream=False # just get the results, don't stream them\n",
    "    )\n",
    "    return response['message']['content']\n",
    "\n",
    "display(Markdown(get_llama_response(question)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa1e9987-7b6d-49c1-9a81-b1a92aceea72",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}