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.
199 lines
7.6 KiB
199 lines
7.6 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" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"API key found and looks good so far!\n", |
|
"Hello! It’s great to hear from you! How can I assist you today?\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# Edward Donner Website Summary\n", |
|
"\n", |
|
"Edward Donner's website serves as a personal platform where he shares insights related to code, LLMs (Large Language Models), and his interests in music production and technology. \n", |
|
"\n", |
|
"## About Ed\n", |
|
"- Ed is the co-founder and CTO of Nebula.io, an AI-driven company focused on talent discovery and engagement.\n", |
|
"- He previously founded untapt, an AI startup that was acquired in 2021.\n", |
|
"\n", |
|
"## Features\n", |
|
"- **Connect Four**: A unique arena designed for LLMs to engage in simulated diplomacy and strategy.\n", |
|
"- **Outsmart**: Another interactive feature related to LLMs.\n", |
|
"\n", |
|
"## News and Announcements\n", |
|
"- **January 23, 2025**: Announcement of a workshop titled \"LLM Workshop – Hands-on with Agents\" providing resources for participants.\n", |
|
"- **December 21, 2024**: Welcoming message for \"SuperDataScientists.\"\n", |
|
"- **November 13, 2024**: Resources available for the topic \"Mastering AI and LLM Engineering.\"\n", |
|
"- **October 16, 2024**: Resources provided for transitioning from a software engineer to an AI data scientist.\n", |
|
"\n", |
|
"The website emphasizes Ed's passion for technology and AI, highlighting his professional achievements and ongoing projects." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"#!/usr/bin/env python\n", |
|
"# coding: utf-8\n", |
|
"\n", |
|
"# # YOUR FIRST LAB\n", |
|
"# ## Your first Frontier LLM Project\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", |
|
"# # Connecting to OpenAI (or Ollama)\n", |
|
"# Load environment variables in a file called .env\n", |
|
"load_dotenv(override=True)\n", |
|
"api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"\n", |
|
"# Check the key\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", |
|
"\n", |
|
"# Open API connection\n", |
|
"openai = OpenAI()\n", |
|
"\n", |
|
"# To give you a preview -- calling OpenAI with these messages is this easy: openai.chat.completions.create(model, messages)\n", |
|
"message = \"Hello, GPT! This is my first ever message to you! Hi!\"\n", |
|
"response = openai.chat.completions.create(\n", |
|
" model=\"gpt-4o-mini\", \n", |
|
" messages=[\n", |
|
" {\"role\":\"user\", \"content\":message}\n", |
|
" ]\n", |
|
")\n", |
|
"print(response.choices[0].message.content)\n", |
|
"\n", |
|
"# A class to represent a Webpage\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)\n", |
|
"\n", |
|
"# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\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.\"\n", |
|
"\n", |
|
"user_prompt_content = \"\\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", |
|
"\n", |
|
"# A function that writes a User Prompt that asks for summaries of websites:\n", |
|
"def user_prompt_for(website):\n", |
|
" user_prompt = f\"You are looking at a website titled {website.title}\"\n", |
|
" user_prompt += user_prompt_content\n", |
|
" user_prompt += website.text\n", |
|
" return user_prompt\n", |
|
"\n", |
|
"# See how this function creates exactly the format above\n", |
|
"def messages_for(website):\n", |
|
" return [\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
|
" ]\n", |
|
"\n", |
|
"# Try this out, and then try for a few more websites\n", |
|
"# messages_for(ed)\n", |
|
"\n", |
|
"# And now: call the OpenAI API. You will get very familiar with this!\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\n", |
|
"\n", |
|
"# A function to display this nicely in the Jupyter output, using markdown\n", |
|
"def display_summary(url):\n", |
|
" summary = summarize(url)\n", |
|
" display(Markdown(summary))\n", |
|
"\n", |
|
"website_url = \"https://edwarddonner.com\"\n", |
|
"\n", |
|
"# Let's try one out. Change the website and add print statements to follow along.\n", |
|
"\n", |
|
"ed = Website(website_url)\n", |
|
"display_summary(website_url)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "b2714e98-8f45-443e-99f8-918e2d61ae36", |
|
"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": "3.11.12" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|