From d73ac9aa17f149b27c45846cb696d62e2968c89e Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Thu, 19 Dec 2024 02:27:38 +1100 Subject: [PATCH 1/2] day 1 javascript webiste challenged added --- ...-webscraping-selenium-for-javascript.ipynb | 871 ++++++++++++++++++ 1 file changed, 871 insertions(+) create mode 100644 week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb diff --git a/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb b/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb new file mode 100644 index 0000000..8ec191a --- /dev/null +++ b/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb @@ -0,0 +1,871 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9", + "metadata": {}, + "source": [ + "# Instant Gratification\n", + "\n", + "## Your first Frontier LLM Project!\n", + "\n", + "Let's build a useful LLM solution - in a matter of minutes.\n", + "\n", + "By the end of this course, you will have built an autonomous Agentic AI solution with 7 agents that collaborate to solve a business problem. All in good time! We will start with something smaller...\n", + "\n", + "Our goal is to code a new kind of Web Browser. Give it a URL, and it will respond with a summary. The Reader's Digest of the internet!!\n", + "\n", + "Before starting, you should have completed the setup for [PC](../SETUP-PC.md) or [Mac](../SETUP-mac.md) and you hopefully launched this jupyter lab from within the project root directory, with your environment activated.\n", + "\n", + "## If you're new to Jupyter Lab\n", + "\n", + "Welcome to the wonderful world of Data Science experimentation! Once you've used Jupyter Lab, you'll wonder how you ever lived without it. Simply click in each \"cell\" with code in it, such as the cell immediately below this text, and hit Shift+Return to execute that cell. As you wish, you can add a cell with the + button in the toolbar, and print values of variables, or try out variations. \n", + "\n", + "I've written a notebook called [Guide to Jupyter](Guide%20to%20Jupyter.ipynb) to help you get more familiar with Jupyter Labs, including adding Markdown comments, using `!` to run shell commands, and `tqdm` to show progress.\n", + "\n", + "If you prefer to work in IDEs like VSCode or Pycharm, they both work great with these lab notebooks too. \n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "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": "markdown", + "id": "6900b2a8-6384-4316-8aaa-5e519fca4254", + "metadata": {}, + "source": [ + "# Connecting to OpenAI\n", + "\n", + "The next cell is where we load in the environment variables in your `.env` file and connect to OpenAI.\n", + "\n", + "## Troubleshooting if you have problems:\n", + "\n", + "Head over to the [troubleshooting](troubleshooting.ipynb) notebook in this folder for step by step code to identify the root cause and fix it!\n", + "\n", + "If you make a change, try restarting the \"Kernel\" (the python process sitting behind this notebook) by Kernel menu >> Restart Kernel and Clear Outputs of All Cells. Then try this notebook again, starting at the top.\n", + "\n", + "Or, contact me! Message me or email ed@edwarddonner.com and we will get this to work.\n", + "\n", + "Any concerns about API costs? See my notes in the README - costs should be minimal, and you can control it at every point. You can also use Ollama as a free alternative, which we discuss during Day 2." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "7b87cadb-d513-4303-baee-a37b6f938e4d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "API key found and looks good so far!\n" + ] + } + ], + "source": [ + "# Load environment variables in a file called .env\n", + "\n", + "load_dotenv()\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!\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "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", + "# If it STILL doesn't work (horrors!) then please see the troubleshooting notebook, or try the below line instead:\n", + "# openai = OpenAI(api_key=\"your-key-here-starting-sk-proj-\")" + ] + }, + { + "cell_type": "markdown", + "id": "442fc84b-0815-4f40-99ab-d9a5da6bda91", + "metadata": {}, + "source": [ + "# Let's make a quick call to a Frontier model to get started, as a preview!" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "a58394bf-1e45-46af-9bfd-01e24da6f49a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Hello! Welcome! I'm glad to have your first message here. How can I assist you today?\n" + ] + } + ], + "source": [ + "# To give you a preview -- calling OpenAI with these messages is this easy:\n", + "\n", + "message = \"Hello, GPT! This is my first ever message to you! Hi!\"\n", + "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=[{\"role\":\"user\", \"content\":message}])\n", + "print(response.choices[0].message.content)" + ] + }, + { + "cell_type": "markdown", + "id": "2aa190e5-cb31-456a-96cc-db109919cd78", + "metadata": {}, + "source": [ + "## OK onwards with our first project" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "c5e793b2-6775-426a-a139-4848291d0463", + "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": 8, + "id": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Home - Edward Donner\n", + "Home\n", + "Outsmart\n", + "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", + "About\n", + "Posts\n", + "Well, hi there.\n", + "I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n", + "very\n", + "amateur) and losing myself in\n", + "Hacker News\n", + ", nodding my head sagely to things I only half understand.\n", + "I’m the co-founder and CTO of\n", + "Nebula.io\n", + ". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n", + "acquired in 2021\n", + ".\n", + "We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n", + "patented\n", + "our matching model, and our award-winning platform has happy customers and tons of press coverage.\n", + "Connect\n", + "with me for more!\n", + "November 13, 2024\n", + "Mastering AI and LLM Engineering – Resources\n", + "October 16, 2024\n", + "From Software Engineer to AI Data Scientist – resources\n", + "August 6, 2024\n", + "Outsmart LLM Arena – a battle of diplomacy and deviousness\n", + "June 26, 2024\n", + "Choosing the Right LLM: Toolkit and Resources\n", + "Navigation\n", + "Home\n", + "Outsmart\n", + "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", + "About\n", + "Posts\n", + "Get in touch\n", + "ed [at] edwarddonner [dot] com\n", + "www.edwarddonner.com\n", + "Follow me\n", + "LinkedIn\n", + "Twitter\n", + "Facebook\n", + "Subscribe to newsletter\n", + "Type your email…\n", + "Subscribe\n" + ] + } + ], + "source": [ + "# Let's try one out. Change the website and add print statements to follow along.\n", + "\n", + "ed = Website(\"https://edwarddonner.com\")\n", + "print(ed.title)\n", + "print(ed.text)" + ] + }, + { + "cell_type": "markdown", + "id": "6a478a0c-2c53-48ff-869c-4d08199931e1", + "metadata": {}, + "source": [ + "## Types of prompts\n", + "\n", + "You may know this already - but if not, you will get very familiar with it!\n", + "\n", + "Models like GPT4o have been trained to receive instructions in a particular way.\n", + "\n", + "They expect to receive:\n", + "\n", + "**A system prompt** that tells them what task they are performing and what tone they should use\n", + "\n", + "**A user prompt** -- the conversation starter that they should reply to" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "abdb8417-c5dc-44bc-9bee-2e059d162699", + "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": 10, + "id": "f0275b1b-7cfe-4f9d-abfa-7650d378da0c", + "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": 11, + "id": "26448ec4-5c00-4204-baec-7df91d11ff2e", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "You are looking at a website titled Home - Edward Donner\n", + "The contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\n", + "\n", + "Home\n", + "Outsmart\n", + "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", + "About\n", + "Posts\n", + "Well, hi there.\n", + "I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n", + "very\n", + "amateur) and losing myself in\n", + "Hacker News\n", + ", nodding my head sagely to things I only half understand.\n", + "I’m the co-founder and CTO of\n", + "Nebula.io\n", + ". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n", + "acquired in 2021\n", + ".\n", + "We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n", + "patented\n", + "our matching model, and our award-winning platform has happy customers and tons of press coverage.\n", + "Connect\n", + "with me for more!\n", + "November 13, 2024\n", + "Mastering AI and LLM Engineering – Resources\n", + "October 16, 2024\n", + "From Software Engineer to AI Data Scientist – resources\n", + "August 6, 2024\n", + "Outsmart LLM Arena – a battle of diplomacy and deviousness\n", + "June 26, 2024\n", + "Choosing the Right LLM: Toolkit and Resources\n", + "Navigation\n", + "Home\n", + "Outsmart\n", + "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", + "About\n", + "Posts\n", + "Get in touch\n", + "ed [at] edwarddonner [dot] com\n", + "www.edwarddonner.com\n", + "Follow me\n", + "LinkedIn\n", + "Twitter\n", + "Facebook\n", + "Subscribe to newsletter\n", + "Type your email…\n", + "Subscribe\n" + ] + } + ], + "source": [ + "print(user_prompt_for(ed))" + ] + }, + { + "cell_type": "markdown", + "id": "ea211b5f-28e1-4a86-8e52-c0b7677cadcc", + "metadata": {}, + "source": [ + "## Messages\n", + "\n", + "The API from OpenAI expects to receive messages in a particular structure.\n", + "Many of the other APIs share this structure:\n", + "\n", + "```\n", + "[\n", + " {\"role\": \"system\", \"content\": \"system message goes here\"},\n", + " {\"role\": \"user\", \"content\": \"user message goes here\"}\n", + "]\n", + "\n", + "To give you a preview, the next 2 cells make a rather simple call - we won't stretch the might GPT (yet!)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "f25dcd35-0cd0-4235-9f64-ac37ed9eaaa5", + "metadata": {}, + "outputs": [], + "source": [ + "messages = [\n", + " {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", + " {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", + "]" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "21ed95c5-7001-47de-a36d-1d6673b403ce", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Oh, I don’t know, maybe it’s 22? Just kidding—it's 4. Basic math is still safe!\n" + ] + } + ], + "source": [ + "# To give you a preview -- calling OpenAI with system and user messages:\n", + "\n", + "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", + "print(response.choices[0].message.content)" + ] + }, + { + "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": 14, + "id": "0134dfa4-8299-48b5-b444-f2a8c3403c88", + "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": 15, + "id": "36478464-39ee-485c-9f3f-6a4e458dbc9c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'role': 'system',\n", + " 'content': 'You are an assistant that analyzes the contents of a website and provides a short summary, ignoring text that might be navigation related. Respond in markdown.'},\n", + " {'role': 'user',\n", + " 'content': 'You are looking at a website titled Home - Edward Donner\\nThe contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\\n\\nHome\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nWell, hi there.\\nI’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\\nvery\\namateur) and losing myself in\\nHacker News\\n, nodding my head sagely to things I only half understand.\\nI’m the co-founder and CTO of\\nNebula.io\\n. We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\\nacquired in 2021\\n.\\nWe work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\\npatented\\nour matching model, and our award-winning platform has happy customers and tons of press coverage.\\nConnect\\nwith me for more!\\nNovember 13, 2024\\nMastering AI and LLM Engineering – Resources\\nOctober 16, 2024\\nFrom Software Engineer to AI Data Scientist – resources\\nAugust 6, 2024\\nOutsmart LLM Arena – a battle of diplomacy and deviousness\\nJune 26, 2024\\nChoosing the Right LLM: Toolkit and Resources\\nNavigation\\nHome\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nGet in touch\\ned [at] edwarddonner [dot] com\\nwww.edwarddonner.com\\nFollow me\\nLinkedIn\\nTwitter\\nFacebook\\nSubscribe to newsletter\\nType your email…\\nSubscribe'}]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Try this out, and then try for a few more websites\n", + "\n", + "messages_for(ed)" + ] + }, + { + "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": 16, + "id": "905b9919-aba7-45b5-ae65-81b3d1d78e34", + "metadata": {}, + "outputs": [], + "source": [ + "# And now: call the OpenAI API. You will get very familiar with this!\n", + "\n", + "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": 17, + "id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'# Summary of Edward Donner\\'s Website\\n\\nEdward Donner\\'s website serves as a personal and professional hub for his interests and projects, particularly in the domains of code writing, large language models (LLMs), and artificial intelligence (AI). \\n\\n## About Ed\\n- Ed describes himself as a coder and enthusiast of LLMs, highlighting his background as the co-founder and CTO of Nebula.io, a company focused on leveraging AI to enhance talent discovery and management. \\n- He has a history as the founder and CEO of the AI startup untapt, which was acquired in 2021.\\n- Outside of his tech interests, Ed enjoys DJing and amateur electronic music production.\\n\\n## Key Projects and Features\\n- **Outsmart**: A platform where LLMs compete against each other in strategic scenarios.\\n \\n## Recent Posts\\n- **November 13, 2024**: \"Mastering AI and LLM Engineering – Resources\" - A collection of resources for those looking to deepen their skills in AI and LLM engineering.\\n- **October 16, 2024**: \"From Software Engineer to AI Data Scientist – Resources\" - Guidance and tools for transitioning from software engineering to AI data science roles.\\n- **August 6, 2024**: \"Outsmart LLM Arena – a battle of diplomacy and deviousness\" - A focus on the unique features of the Outsmart program.\\n- **June 26, 2024**: \"Choosing the Right LLM: Toolkit and Resources\" - A resource list for selecting suitable LLMs for various applications.\\n\\nOverall, the website presents Ed as a tech-savvy individual with a passion for sharing knowledge and resources in the AI field.'" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summarize(\"https://edwarddonner.com\")" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "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": 19, + "id": "3018853a-445f-41ff-9560-d925d1774b2f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "# Website Summary: Edward Donner\n", + "\n", + "Edward Donner's website showcases his interests and professional background, particularly in coding and experimenting with large language models (LLMs). He is the co-founder and CTO of Nebula.io, a company focused on applying AI to enhance talent discovery and management. Previously, he founded the AI startup untapt, which was acquired in 2021. \n", + "\n", + "## Key Features:\n", + "- **Outsmart**: A unique platform where LLMs compete in strategy games that test diplomacy and cunning. \n", + "- **Blog Posts**: Various posts offering resources for mastering AI and LLM engineering, transitioning from software engineering to AI data science, and guidance on choosing the right LLM.\n", + "\n", + "## Recent Announcements:\n", + "- **November 13, 2024**: Post on \"Mastering AI and LLM Engineering.\"\n", + "- **October 16, 2024**: Insights on \"From Software Engineer to AI Data Scientist.\"\n", + "- **August 6, 2024**: Information on \"Outsmart LLM Arena.\"\n", + "- **June 26, 2024**: Resources for \"Choosing the Right LLM.\" \n", + "\n", + "Overall, the website serves as a platform for sharing knowledge and fostering connections within the AI and LLM community." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_summary(\"https://edwarddonner.com\")" + ] + }, + { + "cell_type": "markdown", + "id": "b3bcf6f4-adce-45e9-97ad-d9a5d7a3a624", + "metadata": {}, + "source": [ + "# Let's try more websites\n", + "\n", + "Note that this will only work on websites that can be scraped using this simplistic approach.\n", + "\n", + "Websites that are rendered with Javascript, like React apps, won't show up. See the community-contributions folder for a Selenium implementation that gets around this. You'll need to read up on installing Selenium (ask ChatGPT!)\n", + "\n", + "Also Websites protected with CloudFront (and similar) may give 403 errors - many thanks Andy J for pointing this out.\n", + "\n", + "But many websites will work just fine!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "45d83403-a24c-44b5-84ac-961449b4008f", + "metadata": {}, + "outputs": [], + "source": [ + "display_summary(\"https://cnn.com\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "75e9fd40-b354-4341-991e-863ef2e59db7", + "metadata": {}, + "outputs": [], + "source": [ + "display_summary(\"https://anthropic.com\")" + ] + }, + { + "cell_type": "markdown", + "id": "36ed9f14-b349-40e9-a42c-b367e77f8bda", + "metadata": {}, + "source": [ + "## An extra exercise for those who enjoy web scraping\n", + "\n", + "You may notice that if you try `display_summary(\"https://openai.com\")` - it doesn't work! That's because OpenAI has a fancy website that uses Javascript. There are many ways around this that some of you might be familiar with. For example, Selenium is a hugely popular framework that runs a browser behind the scenes, renders the page, and allows you to query it. If you have experience with Selenium, Playwright or similar, then feel free to improve the Website class to use them. In the community-contributions folder, you'll find an example Selenium solution from a student (thank you!)" + ] + }, + { + "cell_type": "markdown", + "id": "eeab24dc-5f90-4570-b542-b0585aca3eb6", + "metadata": {}, + "source": [ + "# Sharing your code\n", + "\n", + "I'd love it if you share your code afterwards so I can share it with others! You'll notice that some students have already made changes (including a Selenium implementation) which you will find in the community-contributions folder. If you'd like add your changes to that folder, submit a Pull Request with your new versions in that folder and I'll merge your changes.\n", + "\n", + "If you're not an expert with git (and I am not!) then GPT has given some nice instructions on how to submit a Pull Request. It's a bit of an involved process, but once you've done it once it's pretty clear. As a pro-tip: it's best if you clear the outputs of your Jupyter notebooks (Edit >> Clean outputs of all cells, and then Save) for clean notebooks.\n", + "\n", + "PR instructions courtesy of an AI friend: https://chatgpt.com/share/670145d5-e8a8-8012-8f93-39ee4e248b4c" + ] + }, + { + "cell_type": "markdown", + "id": "0f62a788", + "metadata": {}, + "source": [ + "# **Web Scraping for JavaScript Website**" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dca2768e", + "metadata": {}, + "outputs": [], + "source": [ + "# !pip install selenium\n", + "# !pip install undetected-chromedriver" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "682eff74-55c4-4d4b-b267-703edbc293c7", + "metadata": {}, + "outputs": [], + "source": [ + "import undetected_chromedriver as uc\n", + "from selenium.webdriver.common.by import By\n", + "from selenium.webdriver.support.ui import WebDriverWait\n", + "from selenium.webdriver.support import expected_conditions as EC\n", + "import time\n", + "from bs4 import BeautifulSoup" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "90ca6dd0", + "metadata": {}, + "outputs": [], + "source": [ + "class WebsiteCrawler:\n", + " def __init__(self, url, wait_time=20, chrome_binary_path=None):\n", + " \"\"\"\n", + " Initialize the WebsiteCrawler using Selenium to scrape JavaScript-rendered content.\n", + " \"\"\"\n", + " self.url = url\n", + " self.wait_time = wait_time\n", + "\n", + " options = uc.ChromeOptions()\n", + " options.add_argument(\"--disable-gpu\")\n", + " options.add_argument(\"--no-sandbox\")\n", + " options.add_argument(\"--disable-dev-shm-usage\")\n", + " options.add_argument(\"--disable-blink-features=AutomationControlled\")\n", + " options.add_argument(\"start-maximized\")\n", + " options.add_argument(\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", + " if chrome_binary_path:\n", + " options.binary_location = chrome_binary_path\n", + "\n", + " self.driver = uc.Chrome(options=options)\n", + "\n", + " try:\n", + " # Load the URL\n", + " self.driver.get(url)\n", + "\n", + " # Wait for Cloudflare or similar checks\n", + " time.sleep(10)\n", + "\n", + " # Ensure the main content is loaded\n", + " WebDriverWait(self.driver, self.wait_time).until(\n", + " EC.presence_of_element_located((By.TAG_NAME, \"main\"))\n", + " )\n", + "\n", + " # Extract the main content\n", + " main_content = self.driver.find_element(By.CSS_SELECTOR, \"main\").get_attribute(\"outerHTML\")\n", + "\n", + " # Parse with BeautifulSoup\n", + " soup = BeautifulSoup(main_content, \"html.parser\")\n", + " self.title = self.driver.title if self.driver.title else \"No title found\"\n", + " self.text = soup.get_text(separator=\"\\n\", strip=True)\n", + "\n", + " except Exception as e:\n", + " print(f\"Error occurred: {e}\")\n", + " self.title = \"Error occurred\"\n", + " self.text = \"\"\n", + "\n", + " finally:\n", + " self.driver.quit()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "947eac30", + "metadata": {}, + "outputs": [], + "source": [ + "chrome_path = \"C:/Program Files/Google/Chrome/Application/chrome.exe\"\n", + "url = \"https://www.canva.com/\"\n" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "2cba8c91", + "metadata": {}, + "outputs": [], + "source": [ + "def new_summary(url, chrome_path):\n", + " web = WebsiteCrawler(url, 30, chrome_path)\n", + " response = openai.chat.completions.create(\n", + " model = \"gpt-4o-mini\",\n", + " messages = messages_for(web)\n", + " )\n", + "\n", + " web_summary = response.choices[0].message.content\n", + " \n", + " return display(Markdown(web_summary))" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "da7f7b16", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "# Canva: Visual Suite for Everyone\n", + "\n", + "Canva is a user-friendly design platform that allows individuals and teams to create a variety of professional designs, including posters, logos, presentations, and more. It offers options for different users, including a free version for individuals and premium plans for teams and organizations.\n", + "\n", + "## Key Features:\n", + "- **Design Templates**: A wide range of customizable templates for various purposes, such as social media, business cards, and events.\n", + "- **AI-Powered Tools**: Features like Magic Write for copy generation and Magic Edit for photo transformation enhance design capabilities.\n", + "- **Collaboration**: Real-time collaborative tools for teams to design and provide feedback on projects together.\n", + "- **Printing Services**: Canva offers printing services for various products, with free delivery and sustainable practices.\n", + "- **Educational and Nonprofit Support**: Free premium features are available for educational organizations and nonprofits.\n", + "\n", + "## User Testimonials:\n", + "Business leaders commend Canva for its efficiency in streamlining design processes and maintaining brand consistency across teams.\n", + "\n", + "## Sustainability Efforts:\n", + "Canva emphasizes sustainability by planting trees for printed orders and operating with carbon neutrality.\n", + "\n", + "Overall, Canva caters to a diverse audience, from individuals to large organizations, by providing accessible and innovative design solutions." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "new_summary(url, chrome_path)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "7880ce6a", + "metadata": {}, + "outputs": [], + "source": [ + "url = \"https://openai.com\"" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "337b06da", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "# OpenAI Website Summary\n", + "\n", + "OpenAI is focused on creating safe artificial general intelligence (AGI) that benefits humanity. The site features various products and initiatives aimed at enhancing creativity and productivity through advanced AI technologies. \n", + "\n", + "## Key Highlights:\n", + "\n", + "### Products and Features\n", + "- **Sora**: A new platform that allows users to bring their imagination to life through text, images, or videos.\n", + "- **ChatGPT**: Includes various applications such as ChatGPT Pro, desktop integration, and a new search feature. Recent upgrades allow ChatGPT to analyze images, hear, and speak.\n", + "- **Canvas**: A new writing and coding interface integrated within ChatGPT.\n", + "- **o1 Models**: A series of AI models designed to improve response time by incorporating deeper reasoning.\n", + "\n", + "### Announcements\n", + "- **Partnerships**: OpenAI announced a partnership with Apple to explore advancements in AI technology.\n", + "- **New Features**: Introduced improvements to the fine-tuning API and expanded custom models program, aiming to better serve developers and enterprise users.\n", + "- **Collaboration with Media**: A partnership with Le Monde and Prisa Media intends to bring French and Spanish news content to ChatGPT.\n", + "\n", + "### Research and Safety\n", + "- Ongoing research efforts are focused on building a safer AI framework, including advanced tools for compliance within the ChatGPT Enterprise suite.\n", + "- Publications addressing AI's benefits and risks, including topics like synthetic voices and biological threats, are regularly updated.\n", + "\n", + "For more detailed insights, the website facilitates exploration of their product offerings, research publications, and the newest tools for developers and businesses." + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "new_summary(url, chrome_path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9a5d69ea", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "llm_env", + "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": "3.11.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} From 2c88c787ad7a9364f8e2f5516dad9e44e5b46a4c Mon Sep 17 00:00:00 2001 From: codenigma1 Date: Thu, 19 Dec 2024 02:38:01 +1100 Subject: [PATCH 2/2] day 1 webscraping challenge completed by selenium and clear output cell --- ...-webscraping-selenium-for-javascript.ipynb | 288 ++---------------- 1 file changed, 20 insertions(+), 268 deletions(-) diff --git a/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb b/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb index 8ec191a..6b7a266 100644 --- a/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb +++ b/week1/community-contributions/day1-webscraping-selenium-for-javascript.ipynb @@ -67,18 +67,10 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "id": "7b87cadb-d513-4303-baee-a37b6f938e4d", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "API key found and looks good so far!\n" - ] - } - ], + "outputs": [], "source": [ "# Load environment variables in a file called .env\n", "\n", @@ -121,18 +113,10 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "id": "a58394bf-1e45-46af-9bfd-01e24da6f49a", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Hello! Welcome! I'm glad to have your first message here. How can I assist you today?\n" - ] - } - ], + "outputs": [], "source": [ "# To give you a preview -- calling OpenAI with these messages is this easy:\n", "\n", @@ -181,63 +165,10 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "id": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Home - Edward Donner\n", - "Home\n", - "Outsmart\n", - "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", - "About\n", - "Posts\n", - "Well, hi there.\n", - "I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n", - "very\n", - "amateur) and losing myself in\n", - "Hacker News\n", - ", nodding my head sagely to things I only half understand.\n", - "I’m the co-founder and CTO of\n", - "Nebula.io\n", - ". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n", - "acquired in 2021\n", - ".\n", - "We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n", - "patented\n", - "our matching model, and our award-winning platform has happy customers and tons of press coverage.\n", - "Connect\n", - "with me for more!\n", - "November 13, 2024\n", - "Mastering AI and LLM Engineering – Resources\n", - "October 16, 2024\n", - "From Software Engineer to AI Data Scientist – resources\n", - "August 6, 2024\n", - "Outsmart LLM Arena – a battle of diplomacy and deviousness\n", - "June 26, 2024\n", - "Choosing the Right LLM: Toolkit and Resources\n", - "Navigation\n", - "Home\n", - "Outsmart\n", - "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", - "About\n", - "Posts\n", - "Get in touch\n", - "ed [at] edwarddonner [dot] com\n", - "www.edwarddonner.com\n", - "Follow me\n", - "LinkedIn\n", - "Twitter\n", - "Facebook\n", - "Subscribe to newsletter\n", - "Type your email…\n", - "Subscribe\n" - ] - } - ], + "outputs": [], "source": [ "# Let's try one out. Change the website and add print statements to follow along.\n", "\n", @@ -298,65 +229,10 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "id": "26448ec4-5c00-4204-baec-7df91d11ff2e", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "You are looking at a website titled Home - Edward Donner\n", - "The contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\n", - "\n", - "Home\n", - "Outsmart\n", - "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", - "About\n", - "Posts\n", - "Well, hi there.\n", - "I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n", - "very\n", - "amateur) and losing myself in\n", - "Hacker News\n", - ", nodding my head sagely to things I only half understand.\n", - "I’m the co-founder and CTO of\n", - "Nebula.io\n", - ". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n", - "acquired in 2021\n", - ".\n", - "We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n", - "patented\n", - "our matching model, and our award-winning platform has happy customers and tons of press coverage.\n", - "Connect\n", - "with me for more!\n", - "November 13, 2024\n", - "Mastering AI and LLM Engineering – Resources\n", - "October 16, 2024\n", - "From Software Engineer to AI Data Scientist – resources\n", - "August 6, 2024\n", - "Outsmart LLM Arena – a battle of diplomacy and deviousness\n", - "June 26, 2024\n", - "Choosing the Right LLM: Toolkit and Resources\n", - "Navigation\n", - "Home\n", - "Outsmart\n", - "An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n", - "About\n", - "Posts\n", - "Get in touch\n", - "ed [at] edwarddonner [dot] com\n", - "www.edwarddonner.com\n", - "Follow me\n", - "LinkedIn\n", - "Twitter\n", - "Facebook\n", - "Subscribe to newsletter\n", - "Type your email…\n", - "Subscribe\n" - ] - } - ], + "outputs": [], "source": [ "print(user_prompt_for(ed))" ] @@ -395,18 +271,10 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "id": "21ed95c5-7001-47de-a36d-1d6673b403ce", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Oh, I don’t know, maybe it’s 22? Just kidding—it's 4. Basic math is still safe!\n" - ] - } - ], + "outputs": [], "source": [ "# To give you a preview -- calling OpenAI with system and user messages:\n", "\n", @@ -440,24 +308,10 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "id": "36478464-39ee-485c-9f3f-6a4e458dbc9c", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[{'role': 'system',\n", - " 'content': 'You are an assistant that analyzes the contents of a website and provides a short summary, ignoring text that might be navigation related. Respond in markdown.'},\n", - " {'role': 'user',\n", - " 'content': 'You are looking at a website titled Home - Edward Donner\\nThe contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\\n\\nHome\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nWell, hi there.\\nI’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\\nvery\\namateur) and losing myself in\\nHacker News\\n, nodding my head sagely to things I only half understand.\\nI’m the co-founder and CTO of\\nNebula.io\\n. We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\\nacquired in 2021\\n.\\nWe work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\\npatented\\nour matching model, and our award-winning platform has happy customers and tons of press coverage.\\nConnect\\nwith me for more!\\nNovember 13, 2024\\nMastering AI and LLM Engineering – Resources\\nOctober 16, 2024\\nFrom Software Engineer to AI Data Scientist – resources\\nAugust 6, 2024\\nOutsmart LLM Arena – a battle of diplomacy and deviousness\\nJune 26, 2024\\nChoosing the Right LLM: Toolkit and Resources\\nNavigation\\nHome\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nGet in touch\\ned [at] edwarddonner [dot] com\\nwww.edwarddonner.com\\nFollow me\\nLinkedIn\\nTwitter\\nFacebook\\nSubscribe to newsletter\\nType your email…\\nSubscribe'}]" - ] - }, - "execution_count": 15, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# Try this out, and then try for a few more websites\n", "\n", @@ -492,21 +346,10 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "'# Summary of Edward Donner\\'s Website\\n\\nEdward Donner\\'s website serves as a personal and professional hub for his interests and projects, particularly in the domains of code writing, large language models (LLMs), and artificial intelligence (AI). \\n\\n## About Ed\\n- Ed describes himself as a coder and enthusiast of LLMs, highlighting his background as the co-founder and CTO of Nebula.io, a company focused on leveraging AI to enhance talent discovery and management. \\n- He has a history as the founder and CEO of the AI startup untapt, which was acquired in 2021.\\n- Outside of his tech interests, Ed enjoys DJing and amateur electronic music production.\\n\\n## Key Projects and Features\\n- **Outsmart**: A platform where LLMs compete against each other in strategic scenarios.\\n \\n## Recent Posts\\n- **November 13, 2024**: \"Mastering AI and LLM Engineering – Resources\" - A collection of resources for those looking to deepen their skills in AI and LLM engineering.\\n- **October 16, 2024**: \"From Software Engineer to AI Data Scientist – Resources\" - Guidance and tools for transitioning from software engineering to AI data science roles.\\n- **August 6, 2024**: \"Outsmart LLM Arena – a battle of diplomacy and deviousness\" - A focus on the unique features of the Outsmart program.\\n- **June 26, 2024**: \"Choosing the Right LLM: Toolkit and Resources\" - A resource list for selecting suitable LLMs for various applications.\\n\\nOverall, the website presents Ed as a tech-savvy individual with a passion for sharing knowledge and resources in the AI field.'" - ] - }, - "execution_count": 17, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "summarize(\"https://edwarddonner.com\")" ] @@ -527,37 +370,10 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": null, "id": "3018853a-445f-41ff-9560-d925d1774b2f", "metadata": {}, - "outputs": [ - { - "data": { - "text/markdown": [ - "# Website Summary: Edward Donner\n", - "\n", - "Edward Donner's website showcases his interests and professional background, particularly in coding and experimenting with large language models (LLMs). He is the co-founder and CTO of Nebula.io, a company focused on applying AI to enhance talent discovery and management. Previously, he founded the AI startup untapt, which was acquired in 2021. \n", - "\n", - "## Key Features:\n", - "- **Outsmart**: A unique platform where LLMs compete in strategy games that test diplomacy and cunning. \n", - "- **Blog Posts**: Various posts offering resources for mastering AI and LLM engineering, transitioning from software engineering to AI data science, and guidance on choosing the right LLM.\n", - "\n", - "## Recent Announcements:\n", - "- **November 13, 2024**: Post on \"Mastering AI and LLM Engineering.\"\n", - "- **October 16, 2024**: Insights on \"From Software Engineer to AI Data Scientist.\"\n", - "- **August 6, 2024**: Information on \"Outsmart LLM Arena.\"\n", - "- **June 26, 2024**: Resources for \"Choosing the Right LLM.\" \n", - "\n", - "Overall, the website serves as a platform for sharing knowledge and fostering connections within the AI and LLM community." - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "display_summary(\"https://edwarddonner.com\")" ] @@ -746,40 +562,10 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": null, "id": "da7f7b16", "metadata": {}, - "outputs": [ - { - "data": { - "text/markdown": [ - "# Canva: Visual Suite for Everyone\n", - "\n", - "Canva is a user-friendly design platform that allows individuals and teams to create a variety of professional designs, including posters, logos, presentations, and more. It offers options for different users, including a free version for individuals and premium plans for teams and organizations.\n", - "\n", - "## Key Features:\n", - "- **Design Templates**: A wide range of customizable templates for various purposes, such as social media, business cards, and events.\n", - "- **AI-Powered Tools**: Features like Magic Write for copy generation and Magic Edit for photo transformation enhance design capabilities.\n", - "- **Collaboration**: Real-time collaborative tools for teams to design and provide feedback on projects together.\n", - "- **Printing Services**: Canva offers printing services for various products, with free delivery and sustainable practices.\n", - "- **Educational and Nonprofit Support**: Free premium features are available for educational organizations and nonprofits.\n", - "\n", - "## User Testimonials:\n", - "Business leaders commend Canva for its efficiency in streamlining design processes and maintaining brand consistency across teams.\n", - "\n", - "## Sustainability Efforts:\n", - "Canva emphasizes sustainability by planting trees for printed orders and operating with carbon neutrality.\n", - "\n", - "Overall, Canva caters to a diverse audience, from individuals to large organizations, by providing accessible and innovative design solutions." - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "new_summary(url, chrome_path)" ] @@ -796,44 +582,10 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": null, "id": "337b06da", "metadata": {}, - "outputs": [ - { - "data": { - "text/markdown": [ - "# OpenAI Website Summary\n", - "\n", - "OpenAI is focused on creating safe artificial general intelligence (AGI) that benefits humanity. The site features various products and initiatives aimed at enhancing creativity and productivity through advanced AI technologies. \n", - "\n", - "## Key Highlights:\n", - "\n", - "### Products and Features\n", - "- **Sora**: A new platform that allows users to bring their imagination to life through text, images, or videos.\n", - "- **ChatGPT**: Includes various applications such as ChatGPT Pro, desktop integration, and a new search feature. Recent upgrades allow ChatGPT to analyze images, hear, and speak.\n", - "- **Canvas**: A new writing and coding interface integrated within ChatGPT.\n", - "- **o1 Models**: A series of AI models designed to improve response time by incorporating deeper reasoning.\n", - "\n", - "### Announcements\n", - "- **Partnerships**: OpenAI announced a partnership with Apple to explore advancements in AI technology.\n", - "- **New Features**: Introduced improvements to the fine-tuning API and expanded custom models program, aiming to better serve developers and enterprise users.\n", - "- **Collaboration with Media**: A partnership with Le Monde and Prisa Media intends to bring French and Spanish news content to ChatGPT.\n", - "\n", - "### Research and Safety\n", - "- Ongoing research efforts are focused on building a safer AI framework, including advanced tools for compliance within the ChatGPT Enterprise suite.\n", - "- Publications addressing AI's benefits and risks, including topics like synthetic voices and biological threats, are regularly updated.\n", - "\n", - "For more detailed insights, the website facilitates exploration of their product offerings, research publications, and the newest tools for developers and businesses." - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "new_summary(url, chrome_path)" ]