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.
241 lines
7.3 KiB
241 lines
7.3 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "1b809d22-d170-4db3-a298-1740ce06b534", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"#Udemy Course >> LLM Engineering: Master AI and LLMs\n", |
|
"#Student: Jay\n", |
|
"#Date: Apr 20, 2025\n", |
|
"#Home work: Day1 - Summmarize website using local LLama\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": "code", |
|
"execution_count": 10, |
|
"id": "01e91579-7e32-4c4d-9cc9-c06d13c16209", |
|
"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": 2, |
|
"id": "8d780fba-868c-4216-88f5-1e3ca5ad43ed", |
|
"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": 3, |
|
"id": "839b645f-90ee-434d-b0bd-1cb4e574a8de", |
|
"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": 4, |
|
"id": "ef2453e8-3eca-4f6d-8ccf-9e5274b589a7", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"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": 5, |
|
"id": "6ec397d5-e9b0-411d-8bdb-66605273cb11", |
|
"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": 6, |
|
"id": "76aed9eb-a085-4687-859d-817c771156fa", |
|
"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": "code", |
|
"execution_count": 7, |
|
"id": "26de4682-cf4f-4b7e-8cb2-049f7f46b758", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def summarize(url):\n", |
|
" website = Website(url)\n", |
|
" ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n", |
|
"\n", |
|
" response = ollama_via_openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=messages_for(website) \n", |
|
" )\n", |
|
" return response.choices[0].message.content" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 8, |
|
"id": "16b2532a-d44c-4903-83ec-0b828a2d1b92", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def display_summary(url):\n", |
|
" summary = summarize(url)\n", |
|
" display(Markdown(summary))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 11, |
|
"id": "86af4905-5d5c-47c9-b9b2-27257452ff94", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"**Anthropic Website Summary**\n", |
|
"=====================================\n", |
|
"\n", |
|
"### Mission and Values\n", |
|
"\n", |
|
"Anthropic's mission is to build AI that serves humanity's long-term well-being. They focus on designing powerful technologies with human benefit at their foundation, aiming to demonstrate responsible AI development in practice.\n", |
|
"\n", |
|
"### Notable Releases\n", |
|
"\n", |
|
"#### 2025\n", |
|
"\n", |
|
"* **Claude 3.7 Sonnet**: Anthropic's most intelligent AI model, now available.\n", |
|
"* Recent news articles:\n", |
|
"\t+ \"Tracing the thoughts of a large language model: Interpretability\"\n", |
|
"\t+ \"Anthropic Economic Index: Societal Impacts\"\n", |
|
"\n", |
|
"### Products and Solutions\n", |
|
"\n", |
|
"* **Claude**: A suite of AI tools for building applications and custom experiences with human benefit in mind.\n", |
|
"* **Claude Overview**, **API Platform**, and various other products, including:\n", |
|
"\t+ **Claude 3.5 Haiku**\n", |
|
"\t+ **Claude 3 Opus**\n", |
|
"\n", |
|
"### Research and Commitments\n", |
|
"\n", |
|
"* The Anthropic Academy: A learning platform for developers to build AI solutions with Claude.\n", |
|
"* Responsible scaling policy and alignment science initiatives.\n", |
|
"\n", |
|
"### News Section (Selection)**\n", |
|
"\n", |
|
"Anthropic's recent news articles:\n", |
|
"* \"Claude extended thinking\"\n", |
|
"* \"Alignment faking in large language models\"\n", |
|
"\n", |
|
"### Company Information\n", |
|
"\n", |
|
"For more information on Anthropic, including company, careers, and help resources, follow the provided links." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"display_summary(\"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "a5151062-614e-44ff-b341-d3f64e28aa93", |
|
"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": "3.11.11" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|