You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

230 lines
6.8 KiB

{
"cells": [
{
"cell_type": "markdown",
"id": "56c86bae-1d3c-4c01-b5d6-c8879fec1954",
"metadata": {},
"source": [
"# Wiki Summarizer\n",
"\n",
"This Project takes the name of a topic as input, and checks if the corresponding wiki-page exists. If it does, it parses the web page, and outputs a summary created using the GPT-4o-mini model. \n",
"\n",
"Concepts used: \n",
"- Web Scraping via Beautiful Soup\n",
"- User and System Prompts\n",
"- Use of Open AI GPT-4o-mini via API key"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4820830e-b3b4-426e-b1a2-518e7c7f6c1a",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import requests\n",
"from dotenv import load_dotenv\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display\n",
"from openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2cd7ad51-396c-45c5-9089-f7b21a19da50",
"metadata": {},
"outputs": [],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
"load_dotenv(override=True)\n",
"api_key = os.getenv('OPENAI_API_KEY')\n",
"\n",
"# Check the key\n",
"\n",
"if not api_key:\n",
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
"elif not api_key.startswith(\"sk-proj-\"):\n",
" print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
"elif api_key.strip() != api_key:\n",
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
"else:\n",
" print(\"API key found and looks good so far!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "689421a0-20a1-428b-a8b8-fa239fa6f633",
"metadata": {},
"outputs": [],
"source": [
"# creating an instance\n",
"openai = OpenAI()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "401901ae-7639-4190-98fd-e69374084723",
"metadata": {},
"outputs": [],
"source": [
"def isWiki(url):\n",
" \"\"\"\n",
" Check whether a Wikipedia page exists for a given topic, and \n",
" returns a Boolean value.\n",
" \"\"\"\n",
" response = requests.get(url)\n",
"\n",
" if response.status_code != 200:\n",
" return False\n",
" \n",
" return True"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7cdb14d3-05ea-4de2-a475-d49a5731692e",
"metadata": {},
"outputs": [],
"source": [
"# A class to represent a Webpage\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": "7f6ed50e-0fb5-479e-9845-f62cf25980f7",
"metadata": {},
"outputs": [],
"source": [
"system_prompt = \"You are an educational assistant tasked with helping users understand topics\\\n",
"by providing succinct and clear summaries of requested data. Ignore navigation-related text\\\n",
"and provide answers in markdown format\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b2d77dd9-a94f-49c1-a1be-11d157bd37fb",
"metadata": {},
"outputs": [],
"source": [
"# A function that writes a User Prompt that asks for summaries of wiki pages:\n",
"\n",
"def user_prompt_for(wiki):\n",
" user_prompt = f\"You are looking at a Wikipedia page titled {wiki.title}\"\n",
" user_prompt += \"\\nThe contents of this page is as follows; \\\n",
"please provide a short summary of this website in markdown.\\n\"\n",
" user_prompt += wiki.text\n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d23bcc4-1d89-4bd4-9809-d3a1819aa919",
"metadata": {},
"outputs": [],
"source": [
"def messages_for(wiki):\n",
" return [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt_for(wiki)}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "971bd7fb-2ff8-4494-b386-de69a39c24ff",
"metadata": {},
"outputs": [],
"source": [
"def summarize(url):\n",
" website = Website(url)\n",
" response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages_for(website)\n",
" )\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8fdf9f2-f49e-4d06-ac9e-dfcb8da33d60",
"metadata": {},
"outputs": [],
"source": [
"def display_summary(topic):\n",
" url = f\"https://en.wikipedia.org/wiki/{topic}\"\n",
" if isWiki(url):\n",
" summary = summarize(url)\n",
" display(Markdown(summary))\n",
" else:\n",
" print('A Wikipedia page does not exist for this topic')\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f4758ef0-9b7c-4d3e-9131-e3284dc76b6b",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"topic = input('Enter the name of Wikipedia page for which you would like a summary: ').strip()\n",
"display_summary(topic)"
]
}
],
"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
}