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.
335 lines
17 KiB
335 lines
17 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9", |
|
"metadata": {}, |
|
"source": [ |
|
"# Welcome to your first assignment!\n", |
|
"\n", |
|
"Instructions are below. Please give this a try, and look in the solutions folder if you get stuck (or feel free to ask me!)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "ada885d9-4d42-4d9b-97f0-74fbbbfe93a9", |
|
"metadata": {}, |
|
"source": [ |
|
"<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;\">Just before we get to the assignment --</h2>\n", |
|
" <span style=\"color:#f71;\">I thought I'd take a second to point you at this page of useful resources for the course. This includes links to all the slides.<br/>\n", |
|
" <a href=\"https://edwarddonner.com/2024/11/13/llm-engineering-resources/\">https://edwarddonner.com/2024/11/13/llm-engineering-resources/</a><br/>\n", |
|
" Please keep this bookmarked, and I'll continue to add more useful links there over time.\n", |
|
" </span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "6e9fa1fc-eac5-4d1d-9be4-541b3f2b3458", |
|
"metadata": {}, |
|
"source": [ |
|
"# HOMEWORK EXERCISE ASSIGNMENT\n", |
|
"\n", |
|
"Upgrade the day 1 project to summarize a webpage to use an Open Source model running locally via Ollama rather than OpenAI\n", |
|
"\n", |
|
"You'll be able to use this technique for all subsequent projects if you'd prefer not to use paid APIs.\n", |
|
"\n", |
|
"**Benefits:**\n", |
|
"1. No API charges - open-source\n", |
|
"2. Data doesn't leave your box\n", |
|
"\n", |
|
"**Disadvantages:**\n", |
|
"1. Significantly less power than Frontier Model\n", |
|
"\n", |
|
"## Recap on installation of Ollama\n", |
|
"\n", |
|
"Simply visit [ollama.com](https://ollama.com) and install!\n", |
|
"\n", |
|
"Once complete, the ollama server should already be running locally. \n", |
|
"If you visit: \n", |
|
"[http://localhost:11434/](http://localhost:11434/)\n", |
|
"\n", |
|
"You should see the message `Ollama is running`. \n", |
|
"\n", |
|
"If not, bring up a new Terminal (Mac) or Powershell (Windows) and enter `ollama serve` \n", |
|
"And in another Terminal (Mac) or Powershell (Windows), enter `ollama pull llama3.2` \n", |
|
"Then try [http://localhost:11434/](http://localhost:11434/) again.\n", |
|
"\n", |
|
"If Ollama is slow on your machine, try using `llama3.2:1b` as an alternative. Run `ollama pull llama3.2:1b` from a Terminal or Powershell, and change the code below from `MODEL = \"llama3.2\"` to `MODEL = \"llama3.2:1b\"`" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# imports\n", |
|
"\n", |
|
"import requests\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "29ddd15d-a3c5-4f4e-a678-873f56162724", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Constants\n", |
|
"\n", |
|
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n", |
|
"HEADERS = {\"Content-Type\": \"application/json\"}\n", |
|
"MODEL = \"llama3.2\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 4, |
|
"id": "dac0a679-599c-441f-9bf2-ddc73d35b940", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Create a messages list using the same format that we used for OpenAI\n", |
|
"\n", |
|
"messages = [\n", |
|
" {\"role\": \"user\", \"content\": \"Describe some of the business applications of Generative AI\"}\n", |
|
"]" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 5, |
|
"id": "7bb9c624-14f0-4945-a719-8ddb64f66f47", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"payload = {\n", |
|
" \"model\": MODEL,\n", |
|
" \"messages\": messages,\n", |
|
" \"stream\": False\n", |
|
" }" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 6, |
|
"id": "42b9f644-522d-4e05-a691-56e7658c0ea9", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Generative AI has numerous business applications across various industries. Here are some examples:\n", |
|
"\n", |
|
"1. **Content Generation**: Generative AI can be used to generate high-quality content such as blog posts, social media posts, product descriptions, and more. This can help reduce the time and cost associated with content creation.\n", |
|
"2. **Marketing Automation**: Generative AI can be used to create personalized marketing messages, emails, and ads that are tailored to individual customers' preferences and behaviors.\n", |
|
"3. **Product Design**: Generative AI can be used to design new products, such as furniture, fashion items, or even entire buildings. This can help reduce the time and cost associated with product development.\n", |
|
"4. **Image and Video Generation**: Generative AI can be used to create realistic images and videos that can be used for advertising, marketing, or entertainment purposes.\n", |
|
"5. **Chatbots and Virtual Assistants**: Generative AI can be used to create more sophisticated chatbots and virtual assistants that can understand natural language and provide personalized responses.\n", |
|
"6. **Data Analysis and Visualization**: Generative AI can be used to analyze large datasets and generate visualizations that help businesses make data-driven decisions.\n", |
|
"7. **Predictive Maintenance**: Generative AI can be used to predict when equipment or machinery is likely to fail, allowing businesses to schedule maintenance and reduce downtime.\n", |
|
"8. **Supply Chain Optimization**: Generative AI can be used to optimize supply chain logistics, including predicting demand, managing inventory, and identifying the most efficient routes for delivery.\n", |
|
"9. **Financial Modeling**: Generative AI can be used to create complex financial models that help businesses forecast revenue, predict costs, and make informed investment decisions.\n", |
|
"10. **Customer Service**: Generative AI can be used to provide 24/7 customer support, helping businesses to improve customer satisfaction and reduce the number of complaints.\n", |
|
"\n", |
|
"Some specific examples of companies using Generative AI include:\n", |
|
"\n", |
|
"* **Netflix**: Uses Generative AI to create personalized movie and TV show recommendations.\n", |
|
"* **Microsoft**: Uses Generative AI to generate realistic images and videos for advertising and marketing purposes.\n", |
|
"* **Dyson**: Uses Generative AI to design new products, such as vacuum cleaners and air purifiers.\n", |
|
"* **Amazon**: Uses Generative AI to create personalized product recommendations and improve customer service.\n", |
|
"\n", |
|
"Overall, Generative AI has the potential to transform many business applications across various industries, and its use cases are expected to continue growing in the coming years.\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n", |
|
"print(response.json()['message']['content'])" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "6a021f13-d6a1-4b96-8e18-4eae49d876fe", |
|
"metadata": {}, |
|
"source": [ |
|
"# Introducing the ollama package\n", |
|
"\n", |
|
"And now we'll do the same thing, but using the elegant ollama python package instead of a direct HTTP call.\n", |
|
"\n", |
|
"Under the hood, it's making the same call as above to the ollama server running at localhost:11434" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 7, |
|
"id": "7745b9c4-57dc-4867-9180-61fa5db55eb8", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"Google.com is a multinational technology company that provides a wide range of services and products, but its core focus is on search engine optimization (SEO). Here's a summary:\n", |
|
"\n", |
|
"**Main Services:**\n", |
|
"\n", |
|
"1. **Search Engine**: Google's most popular service allows users to search for information on the internet using keywords.\n", |
|
"2. **Advertising**: Google's advertising platform enables businesses to create targeted ads that appear alongside search results and on partner websites.\n", |
|
"3. **Cloud Computing**: Google Cloud offers a suite of cloud-based services, including storage, computing power, and machine learning algorithms.\n", |
|
"\n", |
|
"**Key Features:**\n", |
|
"\n", |
|
"1. **Algorithms**: Google's proprietary search algorithms aim to provide users with the most relevant and accurate search results.\n", |
|
"2. **Google Maps**: A mapping service that provides directions, street views, and local business listings.\n", |
|
"3. **YouTube**: A video-sharing platform acquired by Google in 2006.\n", |
|
"4. **Gmail**: A free email service with advanced features like spam filtering and integration with other Google services.\n", |
|
"\n", |
|
"**Innovation and Features:**\n", |
|
"\n", |
|
"1. **Artificial Intelligence (AI)**: Google has developed various AI-powered tools, such as Google Assistant and Google Lens.\n", |
|
"2. **Machine Learning**: Google's machine learning capabilities are used to improve search results, advertising, and other products.\n", |
|
"3. **Google Drive**: A cloud storage service that allows users to store and access files from anywhere.\n", |
|
"\n", |
|
"**Other Ventures:**\n", |
|
"\n", |
|
"1. **Hardware**: Google develops its own hardware products, such as Pixel smartphones, Chromebooks, and Chrome OS-based devices.\n", |
|
"2. **Artificial Intelligence Research**: Google invests heavily in AI research, with the goal of developing advanced technologies like self-driving cars and language processing.\n", |
|
"\n", |
|
"Overall, Google.com is a multifaceted platform that offers a wide range of services and products, from search engines to cloud computing and advertising platforms." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"import ollama\n", |
|
"\n", |
|
"messages = [\n", |
|
" {\"role\": \"user\", \"content\": \"Summarize the website google.com\"}\n", |
|
"]\n", |
|
"response = ollama.chat(model=MODEL, messages=messages)\n", |
|
"display(Markdown(response['message']['content']))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "1622d9bb-5c68-4d4e-9ca4-b492c751f898", |
|
"metadata": {}, |
|
"source": [ |
|
"# NOW the exercise for you\n", |
|
"\n", |
|
"Take the code from day1 and incorporate it here, to build a website summarizer that uses Llama 3.2 running locally instead of OpenAI" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "09ffd008-0dc5-47a2-bcbe-c9defe412b17", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdin", |
|
"output_type": "stream", |
|
"text": [ |
|
"Enter a website: https://google.com\n" |
|
] |
|
}, |
|
{ |
|
"ename": "NameError", |
|
"evalue": "name 'requests' is not defined", |
|
"output_type": "error", |
|
"traceback": [ |
|
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", |
|
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", |
|
"Cell \u001b[1;32mIn[1], line 34\u001b[0m\n\u001b[0;32m 30\u001b[0m display(Markdown(response\u001b[38;5;241m.\u001b[39mmessage\u001b[38;5;241m.\u001b[39mcontent))\n\u001b[0;32m 33\u001b[0m user_website \u001b[38;5;241m=\u001b[39m \u001b[38;5;28minput\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEnter a website: \u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 34\u001b[0m \u001b[43msummarize\u001b[49m\u001b[43m(\u001b[49m\u001b[43muser_website\u001b[49m\u001b[43m)\u001b[49m\n", |
|
"Cell \u001b[1;32mIn[1], line 24\u001b[0m, in \u001b[0;36msummarize\u001b[1;34m(url)\u001b[0m\n\u001b[0;32m 23\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msummarize\u001b[39m(url):\n\u001b[1;32m---> 24\u001b[0m website \u001b[38;5;241m=\u001b[39m \u001b[43mWebsite\u001b[49m\u001b[43m(\u001b[49m\u001b[43murl\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 25\u001b[0m messages \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m 26\u001b[0m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrole\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muser\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent\u001b[39m\u001b[38;5;124m\"\u001b[39m: user_prompt_for(website)}\n\u001b[0;32m 27\u001b[0m ]\n\u001b[0;32m 28\u001b[0m response \u001b[38;5;241m=\u001b[39m ollama\u001b[38;5;241m.\u001b[39mchat(model\u001b[38;5;241m=\u001b[39mMODEL, messages\u001b[38;5;241m=\u001b[39mmessages, stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n", |
|
"Cell \u001b[1;32mIn[1], line 8\u001b[0m, in \u001b[0;36mWebsite.__init__\u001b[1;34m(self, url)\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 5\u001b[0m \u001b[38;5;124;03mCreate this Website object from the given url using the BeautifulSoup library\u001b[39;00m\n\u001b[0;32m 6\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 7\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39murl \u001b[38;5;241m=\u001b[39m url\n\u001b[1;32m----> 8\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mrequests\u001b[49m\u001b[38;5;241m.\u001b[39mget(url)\n\u001b[0;32m 9\u001b[0m soup \u001b[38;5;241m=\u001b[39m BeautifulSoup(response\u001b[38;5;241m.\u001b[39mcontent, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhtml.parser\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 10\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtitle \u001b[38;5;241m=\u001b[39m soup\u001b[38;5;241m.\u001b[39mtitle\u001b[38;5;241m.\u001b[39mstring \u001b[38;5;28;01mif\u001b[39;00m soup\u001b[38;5;241m.\u001b[39mtitle \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo title found\u001b[39m\u001b[38;5;124m\"\u001b[39m\n", |
|
"\u001b[1;31mNameError\u001b[0m: name 'requests' is not defined" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"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)\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", |
|
"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\n", |
|
"\n", |
|
"def summarize(url):\n", |
|
" website = Website(url)\n", |
|
" messages = [\n", |
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", |
|
" ]\n", |
|
" response = ollama.chat(model=MODEL, messages=messages, stream=False)\n", |
|
" # display(Markdown(response.choices[0].message.content))\n", |
|
" display(Markdown(response.message.content))\n", |
|
"\n", |
|
"\n", |
|
"user_website = input(\"Enter a website: \")\n", |
|
"summarize(user_website)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "6fe0bf1b-484e-482b-b844-8c23e232ddf8", |
|
"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": "3.11.10" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|