From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
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.
840 lines
38 KiB
840 lines
38 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9", |
|
"metadata": {}, |
|
"source": [ |
|
"# YOUR FIRST LAB\n", |
|
"### Please read this section. This is valuable to get you prepared, even if it's a long read -- it's important stuff.\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're new to the Command Line\n", |
|
"\n", |
|
"Please see these excellent guides: [Command line on PC](https://chatgpt.com/share/67b0acea-ba38-8012-9c34-7a2541052665) and [Command line on Mac](https://chatgpt.com/canvas/shared/67b0b10c93a081918210723867525d2b). \n", |
|
"\n", |
|
"## If you'd prefer to work in IDEs\n", |
|
"\n", |
|
"If you're more comfortable in IDEs like VSCode or Pycharm, they both work great with these lab notebooks too. \n", |
|
"If you'd prefer to work in VSCode, [here](https://chatgpt.com/share/676f2e19-c228-8012-9911-6ca42f8ed766) are instructions from an AI friend on how to configure it for the course.\n", |
|
"\n", |
|
"## If you'd like to brush up your Python\n", |
|
"\n", |
|
"I've added a notebook called [Intermediate Python](Intermediate%20Python.ipynb) to get you up to speed. But you should give it a miss if you already have a good idea what this code does: \n", |
|
"`yield from {book.get(\"author\") for book in books if book.get(\"author\")}`\n", |
|
"\n", |
|
"## I am here to help\n", |
|
"\n", |
|
"If you have any problems at all, please do reach out. \n", |
|
"I'm available through the platform, or at ed@edwarddonner.com, or at https://www.linkedin.com/in/eddonner/ if you'd like to connect (and I love connecting!) \n", |
|
"And this is new to me, but I'm also trying out X/Twitter at [@edwarddonner](https://x.com/edwarddonner) - if you're on X, please show me how it's done 😂 \n", |
|
"\n", |
|
"## More troubleshooting\n", |
|
"\n", |
|
"Please see the [troubleshooting](troubleshooting.ipynb) notebook in this folder to diagnose and fix common problems. At the very end of it is a diagnostics script with some useful debug info.\n", |
|
"\n", |
|
"## If this is old hat!\n", |
|
"\n", |
|
"If you're already comfortable with today's material, please hang in there; you can move swiftly through the first few labs - we will get much more in depth as the weeks progress.\n", |
|
"\n", |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../important.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#900;\">Please read - important note</h2>\n", |
|
" <span style=\"color:#900;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations. If you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>\n", |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../resources.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#f71;\">Treat these labs as a resource</h2>\n", |
|
" <span style=\"color:#f71;\">I push updates to the code regularly. When people ask questions or have problems, I incorporate it in the code, adding more examples or improved commentary. As a result, you'll notice that the code below isn't identical to the videos. Everything from the videos is here; but in addition, I've added more steps and better explanations, and occasionally added new models like DeepSeek. Consider this like an interactive book that accompanies the lectures.\n", |
|
" </span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>\n", |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../business.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#181;\">Business value of these exercises</h2>\n", |
|
" <span style=\"color:#181;\">A final thought. While I've designed these notebooks to be educational, I've also tried to make them enjoyable. We'll do fun things like have LLMs tell jokes and argue with each other. But fundamentally, my goal is to teach skills you can apply in business. I'll explain business implications as we go, and it's worth keeping this in mind: as you build experience with models and techniques, think of ways you could put this into action at work today. Please do contact me if you'd like to discuss more or if you have ideas to bounce off me.</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"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 (or Ollama)\n", |
|
"\n", |
|
"The next cell is where we load in the environment variables in your `.env` file and connect to OpenAI. \n", |
|
"\n", |
|
"If you'd like to use free Ollama instead, please see the README section \"Free Alternative to Paid APIs\", and if you're not sure how to do this, there's a full solution in the solutions folder (day1_with_ollama.ipynb).\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": 2, |
|
"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(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!\")\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"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 in this folder for full instructions" |
|
] |
|
}, |
|
{ |
|
"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": 4, |
|
"id": "a58394bf-1e45-46af-9bfd-01e24da6f49a", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Hello! Welcome! I'm glad to hear from you. How can I assist you today?\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# To give you a preview -- calling OpenAI with these messages is this easy. Any problems, head over to the Troubleshooting notebook.\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": 5, |
|
"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": 6, |
|
"id": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Home - Edward Donner\n", |
|
"Home\n", |
|
"Connect Four\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", |
|
"January 23, 2025\n", |
|
"LLM Workshop – Hands-on with Agents – resources\n", |
|
"December 21, 2024\n", |
|
"Welcome, SuperDataScientists!\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", |
|
"Navigation\n", |
|
"Home\n", |
|
"Connect Four\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": 7, |
|
"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": 8, |
|
"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": 9, |
|
"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", |
|
"Connect Four\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", |
|
"January 23, 2025\n", |
|
"LLM Workshop – Hands-on with Agents – resources\n", |
|
"December 21, 2024\n", |
|
"Welcome, SuperDataScientists!\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", |
|
"Navigation\n", |
|
"Home\n", |
|
"Connect Four\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 mighty GPT (yet!)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 10, |
|
"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": 11, |
|
"id": "21ed95c5-7001-47de-a36d-1d6673b403ce", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Oh, we’re diving into some tough math here! Well, let me put my genius hat on—2 + 2 equals 4. Shocking, I know!\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": 12, |
|
"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": 13, |
|
"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\\nConnect Four\\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!\\nJanuary 23, 2025\\nLLM Workshop – Hands-on with Agents – resources\\nDecember 21, 2024\\nWelcome, SuperDataScientists!\\nNovember 13, 2024\\nMastering AI and LLM Engineering – Resources\\nOctober 16, 2024\\nFrom Software Engineer to AI Data Scientist – resources\\nNavigation\\nHome\\nConnect Four\\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": 13, |
|
"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": 14, |
|
"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": 15, |
|
"id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/plain": [ |
|
"'# Summary of Edward Donner\\'s Website\\n\\nEdward Donner\\'s personal website serves as a platform for sharing his interests and expertise in artificial intelligence, particularly in the field of large language models (LLMs). He introduces himself as a coder and experimenter in this domain, while also mentioning his hobbies, including DJing and electronic music production. \\n\\n## Professional Background\\n- Co-founder and CTO of **Nebula.io**, focusing on leveraging AI to enhance talent discovery and engagement.\\n- Former founder and CEO of AI startup **untapt**, which was acquired in 2021.\\n- He highlights his work with proprietary LLMs and mentions a patented matching model used in his current endeavors.\\n\\n## Recent Posts and Announcements\\n- **January 23, 2025**: Shared resources related to a workshop on LLMs and agents.\\n- **December 21, 2024**: A warm welcome to a new audience, referred to as \"SuperDataScientists.\"\\n- **November 13, 2024**: Resources for mastering AI and LLM engineering were made available.\\n- **October 16, 2024**: He provided resources for software engineers transitioning to AI data scientists.\\n\\nThe site invites visitors to connect with Edward and explore his work further.'" |
|
] |
|
}, |
|
"execution_count": 15, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
} |
|
], |
|
"source": [ |
|
"summarize(\"https://edwarddonner.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 16, |
|
"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": 17, |
|
"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 personal and professional portfolio, showcasing his interests and expertise in coding, large language models (LLMs), and AI technologies. The website highlights his role as co-founder and CTO of Nebula.io, a company focused on leveraging AI to enhance talent discovery and management. He also shares his background as the founder of the AI startup untapt, which was acquired in 2021.\n", |
|
"\n", |
|
"## Recent Announcements\n", |
|
"\n", |
|
"- **January 23, 2025**: LLM Workshop – Hands-on with Agents – resources available.\n", |
|
"- **December 21, 2024**: Welcome note for SuperDataScientists.\n", |
|
"- **November 13, 2024**: Mastering AI and LLM Engineering – resources shared.\n", |
|
"- **October 16, 2024**: Resources for transitioning from Software Engineer to AI Data Scientist.\n", |
|
"\n", |
|
"In addition to his professional pursuits, Ed enjoys DJing and electronic music production, though he humorously notes his lack of practice. He welcomes connections from like-minded individuals interested in technology and AI." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"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": 18, |
|
"id": "45d83403-a24c-44b5-84ac-961449b4008f", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# CNN Summary\n", |
|
"\n", |
|
"CNN is a major news outlet providing comprehensive coverage of breaking news, politics, world events, entertainment, and more. The website features categories including **US News, World, Politics, Business, Health, Entertainment, Sports, Science**, and **Climate**.\n", |
|
"\n", |
|
"### Latest News Highlights:\n", |
|
"- Rory McIlroy won the Masters in a dramatic one-hole playoff.\n", |
|
"- A suspect has been arrested for an arson attempt at Pennsylvania's Governor Shapiro's house.\n", |
|
"- A tragically high-profile shooting incident in Wisconsin allegedly involved a 17-year-old implicated in a plot against Trump.\n", |
|
"- A judge has ruled that a legal permanent US resident can be deported.\n", |
|
"- In global matters, Israeli strikes have led to significant damage and humanitarian crises in Gaza.\n", |
|
"\n", |
|
"### Political Insights:\n", |
|
"- Trump's administration announced temporary tariff exemptions affecting electronic imports from China, which has sparked political discourse.\n", |
|
"- Elizabeth Warren has voiced concerns over potential insider trading amidst Trump's actions.\n", |
|
"\n", |
|
"### International Developments:\n", |
|
"- Ongoing updates on the Ukraine-Russia War reveal significant escalations.\n", |
|
"- Brazil's former president, Jair Bolsonaro, has been hospitalized due to complications from an old injury.\n", |
|
"\n", |
|
"### Additional Sections:\n", |
|
"The site also features **a range of opinion pieces, essays, and analysis**, as well as sections dedicated to health, technology, travel, and entertainment, which include trends, analysis on cultural events, and festival highlights such as Coachella.\n", |
|
"\n", |
|
"CNN continues to emphasize the importance of audience engagement through interactive elements like newsletters and feedback opportunities. The platform provides a crucial space for staying informed about both domestic and international developments." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"display_summary(\"https://cnn.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 22, |
|
"id": "75e9fd40-b354-4341-991e-863ef2e59db7", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# Website Summary: Just a moment...\n", |
|
"\n", |
|
"The website appears to be a temporary loading page indicating that users need to enable JavaScript and cookies in their browser to access the content. There are no specific news or announcements provided on this page, as it primarily serves as an intermediary message before allowing further access to the intended site." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"display_summary(\"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "c951be1a-7f1b-448f-af1f-845978e47e2c", |
|
"metadata": {}, |
|
"source": [ |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../business.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#181;\">Business applications</h2>\n", |
|
" <span style=\"color:#181;\">In this exercise, you experienced calling the Cloud API of a Frontier Model (a leading model at the frontier of AI) for the first time. We will be using APIs like OpenAI at many stages in the course, in addition to building our own LLMs.\n", |
|
"\n", |
|
"More specifically, we've applied this to Summarization - a classic Gen AI use case to make a summary. This can be applied to any business vertical - summarizing the news, summarizing financial performance, summarizing a resume in a cover letter - the applications are limitless. Consider how you could apply Summarization in your business, and try prototyping a solution.</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>\n", |
|
"\n", |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../important.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#900;\">Before you continue - now try yourself</h2>\n", |
|
" <span style=\"color:#900;\">Use the cell below to make your own simple commercial example. Stick with the summarization use case for now. Here's an idea: write something that will take the contents of an email, and will suggest an appropriate short subject line for the email. That's the kind of feature that might be built into a commercial email tool.</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 27, |
|
"id": "00743dac-0e70-45b7-879a-d7293a6f68a6", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"As of my last update in October 2023, I don't have real-time data access to provide the current GDP of India. However, India's GDP has been fluctuating due to various factors such as economic growth rates, inflation, and global market conditions. For the latest and most accurate GDP figures, I recommend checking reliable financial news sources, government publications, or databases such as the World Bank or International Monetary Fund (IMF). These sources will provide you with the most current statistics.\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# Step 1: Create your prompts\n", |
|
"\n", |
|
"system_prompt = \"You are an expert of financial advisor\"\n", |
|
"user_prompt = \"\"\" What is current gdp of india\n", |
|
"\"\"\"\n", |
|
"\n", |
|
"# Step 2: Make the messages list\n", |
|
"\n", |
|
"messages = [\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt}\n", |
|
"]\n", |
|
"\n", |
|
"# Step 3: Call OpenAI\n", |
|
"\n", |
|
"response = openai.chat.completions.create(\n", |
|
" model = \"gpt-4o-mini\",\n", |
|
" messages = messages\n", |
|
" )\n", |
|
"\n", |
|
"print(response.choices[0].message.content)" |
|
] |
|
}, |
|
{ |
|
"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", |
|
"Here are good instructions courtesy of an AI friend: \n", |
|
"https://chatgpt.com/share/677a9cb5-c64c-8012-99e0-e06e88afd293" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "f4484fcf-8b39-4c3f-9674-37970ed71988", |
|
"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": "3.12.7" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|