{ "cells": [ { "cell_type": "markdown", "id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9", "metadata": {}, "source": [ "# Instant Gratification!\n", "\n", "Let's build a useful LLM solution - in a matter of minutes.\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, be sure to have followed the instructions in the \"README\" file, including creating your API key with OpenAI and adding it to the `.env` file.\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, like 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", "If you need to start again, go to Kernel menu >> Restart kernel." ] }, { "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" ] }, { "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", "1. OpenAI takes a few minutes to register after you set up an account. If you receive an error about being over quota, try waiting a few minutes and try again.\n", "2. Also, double check you have the right kind of API token with the right permissions. You should find it on [this webpage](https://platform.openai.com/api-keys) and it should show with Permissions of \"All\". If not, try creating another key by:\n", "- Pressing \"Create new secret key\" on the top right\n", "- Select **Owned by:** you, **Project:** Default project, **Permissions:** All\n", "- Click Create secret key, and use that new key in the code and the `.env` file (it might take a few minutes to activate)\n", "- Do a Kernel >> Restart kernel, and execute the cells in this Jupyter lab starting at the top\n", "4. As a fallback, replace the line `openai = OpenAI()` with `openai = OpenAI(api_key=\"your-key-here\")` - while it's not recommended to hard code tokens in Jupyter lab, because then you can't share your lab with others, it's a workaround for now\n", "5. 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." ] }, { "cell_type": "code", "execution_count": 3, "id": "7b87cadb-d513-4303-baee-a37b6f938e4d", "metadata": {}, "outputs": [], "source": [ "# Load environment variables in a file called .env\n", "\n", "load_dotenv()\n", "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY','your-key-if-not-using-env')\n", "openai = OpenAI()" ] }, { "cell_type": "code", "execution_count": 4, "id": "c5e793b2-6775-426a-a139-4848291d0463", "metadata": {}, "outputs": [], "source": [ "# A class to represent a Webpage\n", "\n", "class Website:\n", " url: str\n", " title: str\n", " text: str\n", "\n", " def __init__(self, url):\n", " self.url = url\n", " response = requests.get(url)\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": 5, "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\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": 6, "id": "abdb8417-c5dc-44bc-9bee-2e059d162699", "metadata": {}, "outputs": [], "source": [ "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": 7, "id": "f0275b1b-7cfe-4f9d-abfa-7650d378da0c", "metadata": {}, "outputs": [], "source": [ "def user_prompt_for(website):\n", " user_prompt = f\"You are looking at a website titled {website.title}\"\n", " user_prompt += \"The 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": "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", "]" ] }, { "cell_type": "code", "execution_count": 8, "id": "0134dfa4-8299-48b5-b444-f2a8c3403c88", "metadata": {}, "outputs": [], "source": [ "def messages_for(website):\n", " return [\n", " {\"role\": \"system\", \"content\": system_prompt},\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": 9, "id": "905b9919-aba7-45b5-ae65-81b3d1d78e34", "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": 10, "id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"# Summary of Edward Donner's Website\\n\\nEdward Donner's website features insights into his interests in coding and experimenting with large language models (LLMs). As the co-founder and CTO of Nebula.io, Donner focuses on leveraging AI to improve talent discovery and management. He has a background in AI startups, highlighting a successful acquisition of his previous venture, untapt, in 2021.\\n\\n## Recent Posts\\n- **November 13, 2024**: *Mastering AI and LLM Engineering – Resources*\\n- **October 16, 2024**: *From Software Engineer to AI Data Scientist – Resources*\\n- **August 6, 2024**: *Outsmart LLM Arena – A Battle of Diplomacy and Deviousness*\\n- **June 26, 2024**: *Choosing the Right LLM: Toolkit and Resources*\\n\\nThe site encourages visitors to connect and shares his passion for technology and music.\"" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "summarize(\"https://edwarddonner.com\")" ] }, { "cell_type": "code", "execution_count": 11, "id": "3d926d59-450e-4609-92ba-2d6f244f1342", "metadata": {}, "outputs": [], "source": [ "def display_summary(url):\n", " summary = summarize(url)\n", " display(Markdown(summary))" ] }, { "cell_type": "code", "execution_count": 12, "id": "3018853a-445f-41ff-9560-d925d1774b2f", "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "# Summary of Edward Donner's Website\n", "\n", "Edward Donner's website serves as a platform for sharing insights and developments related to large language models (LLMs) and their applications. \n", "\n", "### About Edward\n", "Edward describes himself as a programmer and enthusiast of LLMs, with interests in DJing and electronic music production. He is the co-founder and CTO of Nebula.io, a company focused on leveraging AI to enhance talent discovery and engagement in a job context. He previously founded the AI startup untapt, which was acquired in 2021. \n", "\n", "### Featured Content\n", "The website highlights several posts with resources that include:\n", "- **Mastering AI and LLM Engineering** (November 13, 2024)\n", "- **From Software Engineer to AI Data Scientist** (October 16, 2024)\n", "- **Outsmart LLM Arena** (August 6, 2024) - An initiative designed to challenge LLMs in strategic scenarios.\n", "- **Choosing the Right LLM: Toolkit and Resources** (June 26, 2024)\n", "\n", "### Focus\n", "The website primarily emphasizes exploring LLMs and their transformative potential, especially in the realm of talent management. There are also connections to various platforms where Edward can be followed or contacted." ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "display_summary(\"https://edwarddonner.com\")" ] }, { "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. Please push your code afterwards so I can share it with other students!" ] }, { "cell_type": "code", "execution_count": 13, "id": "52ae98bb", "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "# Summary of Website Content\n", "\n", "The website appears to be inaccessible due to a prompt requesting users to enable JavaScript and cookies in their web browser. As a result, no specific content, news, or announcements can be summarized from the site at this time. \n", "\n", "For a full experience and access to content, it is necessary to adjust browser settings accordingly." ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "display_summary(\"https://openai.com\")" ] }, { "cell_type": "code", "execution_count": 14, "id": "5d57e958", "metadata": {}, "outputs": [ { "ename": "ModuleNotFoundError", "evalue": "No module named 'selenium'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[14], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m#Parse webpages which is designed using JavaScript heavely\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;66;03m# download the chorme driver from here as per your version of chrome - https://developer.chrome.com/docs/chromedriver/downloads\u001b[39;00m\n\u001b[1;32m----> 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mselenium\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m webdriver\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mselenium\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mwebdriver\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mchrome\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mservice\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Service\n\u001b[0;32m 5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mselenium\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mwebdriver\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcommon\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mby\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m By\n", "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'selenium'" ] } ], "source": [ "#Parse webpages which is designed using JavaScript heavely\n", "# download the chorme driver from here as per your version of chrome - https://developer.chrome.com/docs/chromedriver/downloads\n", "from selenium import webdriver\n", "from selenium.webdriver.chrome.service import Service\n", "from selenium.webdriver.common.by import By\n", "from selenium.webdriver.chrome.options import Options\n", "\n", "PATH_TO_CHROME_DRIVER = '..\\\\path\\\\to\\\\chromedriver.exe'\n", "\n", "class Website:\n", " url: str\n", " title: str\n", " text: str\n", "\n", " def __init__(self, url):\n", " self.url = url\n", "\n", " options = Options()\n", "\n", " options.add_argument(\"--no-sandbox\")\n", " options.add_argument(\"--disable-dev-shm-usage\")\n", "\n", " service = Service(PATH_TO_CHROME_DRIVER)\n", " driver = webdriver.Chrome(service=service, options=options)\n", " driver.get(url)\n", "\n", " input(\"Please complete the verification in the browser and press Enter to continue...\")\n", " page_source = driver.page_source\n", " driver.quit()\n", "\n", " soup = BeautifulSoup(page_source, 'html.parser')\n", " self.title = soup.title.string if soup.title else \"No title found\"\n", " for irrelevant in soup([\"script\", \"style\", \"img\", \"input\"]):\n", " irrelevant.decompose()\n", " self.text = soup.get_text(separator=\"\\n\", strip=True)" ] }, { "cell_type": "code", "execution_count": null, "id": "65192f6b", "metadata": {}, "outputs": [], "source": [ "display_summary(\"https://openai.com\")" ] }, { "cell_type": "code", "execution_count": null, "id": "f2eb9599", "metadata": {}, "outputs": [], "source": [ "display_summary(\"https://edwarddonner.com\")" ] }, { "cell_type": "code", "execution_count": null, "id": "e7ba56c8", "metadata": {}, "outputs": [], "source": [ "display_summary(\"https://cnn.com\")" ] } ], "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 }