330 lines
10 KiB
Plaintext
330 lines
10 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9ab446e4-219c-4589-aa8f-9386adcf5c60",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"## Project Overview\n",
|
||
"This project combines web scraping with OpenAI’s GPT models to summarize online training content. It extracts material from Microsoft’s **Quantum Computing Fundamentals** learning path, cleans it, and generates concise summaries per lesson as well as an overall course summary. \n",
|
||
"\n",
|
||
"## Key Features\n",
|
||
"- Fetches and parses webpages using **requests** and **BeautifulSoup** \n",
|
||
"- Produces summaries in multiple languages (e.g., English, Spanish, or any language) and at varying levels of detail (short, medium, detailed) \n",
|
||
"- Summarizes individual lessons on demand or processes entire learning paths \n",
|
||
"- Presents results as clean, structured **Markdown** directly in the notebook \n",
|
||
"\n",
|
||
"## Tech Stack\n",
|
||
"- **Model**: GPT-4o-mini \n",
|
||
"- **Language**: Python \n",
|
||
"- **Libraries**: BeautifulSoup, OpenAI \n",
|
||
"\n",
|
||
"## Purpose\n",
|
||
"This project demonstrates how AI can streamline the understanding of technical documentation and online courses by generating multilingual, customizable summaries. \n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
|
||
"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\n",
|
||
"\n",
|
||
"# If you get an error running this cell, then please head over to the troubleshooting notebook!"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "7b87cadb-d513-4303-baee-a37b6f938e4d",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Load environment variables from .env file (not included)\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\")\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\")\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\")\n",
|
||
"else:\n",
|
||
" print(\"API key found and looks good so far!\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "019974d9-f3ad-4a8a-b5f9-0a3719aea2d3",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"openai = OpenAI()\n",
|
||
"\n",
|
||
"# If this doesn't work, try Kernel menu >> Restart Kernel and Clear Outputs Of All Cells, then run the cells from the top of this notebook down.\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c5e793b2-6775-426a-a139-4848291d0463",
|
||
"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": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\n",
|
||
"\n",
|
||
"training_website = Website(\"https://learn.microsoft.com/en-us/training/paths/quantum-computing-fundamentals/\")\n",
|
||
"print(training_website.title)\n",
|
||
"print(training_website.text)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "abdb8417-c5dc-44bc-9bee-2e059d162699",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Create a system prompt function that can use different language and length \n",
|
||
"\n",
|
||
"def build_system_prompt(language=\"Spanish\", length=\"short\"):\n",
|
||
" return f\"\"\"You are an assistant that analyzes the contents of a website and provides a {length} summary, ignoring text that might be navigation related.\n",
|
||
" Respond in 20 words or less markdown, and respond in {language}.\n",
|
||
" \"\"\"\n",
|
||
" \n",
|
||
" \n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "987c95a6-6618-4d22-a2c3-3038a9d3f154",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Create 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 in {language} 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": "8a846c89-81d8-4f48-9d62-7744d76694e2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"print(user_prompt_for(training_website))\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "26448ec4-5c00-4204-baec-7df91d11ff2e",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"print(user_prompt_for(training_website))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d06e8d78-ce4c-4b05-aa8e-17050c82bb47",
|
||
"metadata": {},
|
||
"source": [
|
||
"## And now let's build useful messages for GPT-4o-mini, using a function"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "0134dfa4-8299-48b5-b444-f2a8c3403c88",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\n",
|
||
"def messages_for(website, language=\"Spanish\", length=\"short\"):\n",
|
||
" return [\n",
|
||
" {\"role\": \"system\", \"content\": build_system_prompt(language, length)},\n",
|
||
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
|
||
" ]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "16f49d46-bf55-4c3e-928f-68fc0bf715b0",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Time to bring it together - the API for OpenAI is very simple!"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "425214b8-c5c5-4d7a-8b79-f9e151c9d54f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "905b9919-aba7-45b5-ae65-81b3d1d78e34",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#call the OpenAI API. \n",
|
||
"\n",
|
||
"def summarize(url, language=\"Spanish\", length=\"short\"):\n",
|
||
" website = Website(url)\n",
|
||
" response = openai.chat.completions.create(\n",
|
||
" model=\"gpt-4o-mini\",\n",
|
||
" messages=messages_for(website, language, length)\n",
|
||
" )\n",
|
||
" return response.choices[0].message.content\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1c437357-d004-49f5-95c3-fce38aefcb5c",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#Summarize all the lessons in microsoft quantum computer training, having the option to summarize by lesson, or the training as a whole\n",
|
||
"\n",
|
||
"def summarize_training(path_url, language=\"Spanish\", length=\"short\"):\n",
|
||
" links = get_links_from_path(path_url)\n",
|
||
" print(f\"Found {len(links)} lessons\")\n",
|
||
"\n",
|
||
" all_summaries = []\n",
|
||
"\n",
|
||
" for link in links:\n",
|
||
" print(f\"Summarizing {link}...\")\n",
|
||
" summary = summarize(link, language, length)\n",
|
||
" all_summaries.append(f\"### {link}\\n{summary}\\n\")\n",
|
||
"\n",
|
||
" combined_prompt = \"Here are summaries of each lesson:\\n\\n\" + \"\\n\".join(all_summaries)\n",
|
||
" response = openai.chat.completions.create(\n",
|
||
" model=\"gpt-4o-mini\",\n",
|
||
" messages=[\n",
|
||
" {\"role\": \"system\", \"content\": build_system_prompt(language, length)},\n",
|
||
" {\"role\": \"user\", \"content\": \"Please summarize the entire training path based on these lesson summaries:\\n\\n\" + combined_prompt}\n",
|
||
" ]\n",
|
||
" )\n",
|
||
"\n",
|
||
" return \"\\n\".join(all_summaries) + \"\\n\\n## General Course Summary\\n\" + response.choices[0].message.content\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"summarize(\"https://learn.microsoft.com/en-us/training/paths/quantum-computing-fundamentals/\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "3d926d59-450e-4609-92ba-2d6f244f1342",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# A function to display this nicely in the Jupyter output, using markdown\n",
|
||
"\n",
|
||
"def display_summary(url):\n",
|
||
" summary = summarize(url)\n",
|
||
" display(Markdown(summary))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "3018853a-445f-41ff-9560-d925d1774b2f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"display_summary(\"https://learn.microsoft.com/en-us/training/paths/quantum-computing-fundamentals/\")"
|
||
]
|
||
}
|
||
],
|
||
"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
|
||
}
|