485 lines
17 KiB
Plaintext
485 lines
17 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9",
|
|
"metadata": {},
|
|
"source": [
|
|
"# How to run a cell\n",
|
|
"\n",
|
|
"Press `Shift` + `Return` to run a Cell.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\n",
|
|
"\n",
|
|
"import os, requests, time\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",
|
|
"# 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\")\n",
|
|
"else:\n",
|
|
" print(\"API key found and looks good so far!\")\n",
|
|
"\n",
|
|
"# Instantiate an OpenAI object\n",
|
|
"openai = OpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "442fc84b-0815-4f40-99ab-d9a5da6bda91",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Make a test call to a Frontier model (Open AI) to get started:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a58394bf-1e45-46af-9bfd-01e24da6f49a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"message = \"Hello, GPT! Holla back to this space probe!\"\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": [
|
|
"## Summarization project"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c5e793b2-6775-426a-a139-4848291d0463",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Some websites need 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",
|
|
"\"\"\"\n",
|
|
"A class to represent a Webpage\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": null,
|
|
"id": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Summarize website content\n",
|
|
"website = Website(\"https://rwothoromo.wordpress.com/\")\n",
|
|
"# print(eli.title, \"\\n\", eli.text)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "abdb8417-c5dc-44bc-9bee-2e059d162699",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# A system prompt tells a model like GPT4o what task they are performing and what tone they should use\n",
|
|
"# A user prompt is the conversation starter that they should reply to\n",
|
|
"\n",
|
|
"system_prompt = \"You are an assistant that analyzes the contents of a given website, \\\n",
|
|
"and returns a brief summary, ignoring text that might be navigation-related. \\\n",
|
|
"Respond in markdown.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"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": null,
|
|
"id": "26448ec4-5c00-4204-baec-7df91d11ff2e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(user_prompt_for(website))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f25dcd35-0cd0-4235-9f64-ac37ed9eaaa5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# The API from OpenAI expects to receive messages in a particular structure. Many of the other APIs share this structure:\n",
|
|
"messages = [\n",
|
|
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"}, # system message\n",
|
|
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}, # user message\n",
|
|
"]\n",
|
|
"response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
|
|
"print(response.choices[0].message.content)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0134dfa4-8299-48b5-b444-f2a8c3403c88",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# To build useful messages for GPT-4o-mini\n",
|
|
"\n",
|
|
"def messages_for(website):\n",
|
|
" return [\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
|
|
" ]\n",
|
|
"\n",
|
|
"messages_for(website)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "905b9919-aba7-45b5-ae65-81b3d1d78e34",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Call the OpenAI API.\n",
|
|
"\n",
|
|
"url = \"https://rwothoromo.wordpress.com/\"\n",
|
|
"website = Website(url)\n",
|
|
"\n",
|
|
"def summarize(website):\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": null,
|
|
"id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"summarize(website)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3d926d59-450e-4609-92ba-2d6f244f1342",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# A function to display this nicely in the Jupyter output, using markdown\n",
|
|
"\n",
|
|
"summary = summarize(website)\n",
|
|
"def display_summary(summary):\n",
|
|
" display(Markdown(summary))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3018853a-445f-41ff-9560-d925d1774b2f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"display_summary(summary)\n",
|
|
"# display_summary(summarize(Website(\"https://edwarddonner.com\")))\n",
|
|
"# display_summary(summarize(Website(\"https://cnn.com\")))\n",
|
|
"# display_summary(summarize(Website(\"https://anthropic.com\")))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5a904323-acd9-4c8e-9a17-70df76184590",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Websites protected with CloudFront (and similar) or with JavaScript need a Selenium or Playwright implementation. They return 403\n",
|
|
"\n",
|
|
"# display_summary(summarize(Website(\"https://openai.com\")))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "139ad985",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# To generate the above summary, use selenium\n",
|
|
"\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.support.ui import WebDriverWait\n",
|
|
"from selenium.webdriver.support import expected_conditions as EC\n",
|
|
"\n",
|
|
"class WebsiteSelenium:\n",
|
|
" def __init__(self, url):\n",
|
|
" self.url = url\n",
|
|
" self.title = \"No title found\"\n",
|
|
" self.text = \"\"\n",
|
|
"\n",
|
|
" # Configure Chrome options (headless mode is recommended for server environments)\n",
|
|
" chrome_options = webdriver.ChromeOptions()\n",
|
|
" chrome_options.add_argument(\"--headless\") # Run Chrome in headless mode (without a UI)\n",
|
|
" chrome_options.add_argument(\"--no-sandbox\") # Required for running as root in some environments\n",
|
|
" chrome_options.add_argument(\"--disable-dev-shm-usage\") # Overcomes limited resource problems\n",
|
|
"\n",
|
|
" # Path to your WebDriver executable (e.g., chromedriver)\n",
|
|
" # Make sure to replace this with the actual path to your chromedriver\n",
|
|
" # You might need to download it from: https://chromedriver.chromium.org/downloads and place it in a drivers dir\n",
|
|
" service = Service('./drivers/chromedriver-mac-x64/chromedriver')\n",
|
|
"\n",
|
|
" driver = None\n",
|
|
" try:\n",
|
|
" driver = webdriver.Chrome(service=service, options=chrome_options)\n",
|
|
" driver.get(url)\n",
|
|
"\n",
|
|
" # Wait for the page to load and dynamic content to render\n",
|
|
" # You might need to adjust the wait condition based on the website\n",
|
|
" WebDriverWait(driver, 10).until(\n",
|
|
" EC.presence_of_element_located((By.TAG_NAME, \"body\"))\n",
|
|
" )\n",
|
|
" time.sleep(3) # Give more time for JavaScript to execute\n",
|
|
"\n",
|
|
" # Get the page source after dynamic content has loaded\n",
|
|
" soup = BeautifulSoup(driver.page_source, 'html.parser')\n",
|
|
"\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",
|
|
" except Exception as e:\n",
|
|
" print(f\"Error accessing {url} with Selenium: {e}\")\n",
|
|
" finally:\n",
|
|
" if driver:\n",
|
|
" driver.quit() # Always close the browser\n",
|
|
"\n",
|
|
"display_summary(summarize(WebsiteSelenium(\"https://openai.com\")))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "130d4572",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import asyncio\n",
|
|
"from playwright.async_api import async_playwright\n",
|
|
"import nest_asyncio\n",
|
|
"\n",
|
|
"# Apply nest_asyncio to allow asyncio.run in Jupyter\n",
|
|
"nest_asyncio.apply()\n",
|
|
"\n",
|
|
"class WebsitePlaywright:\n",
|
|
" def __init__(self, url):\n",
|
|
" self.url = url\n",
|
|
" self.title = \"No title found\"\n",
|
|
" self.text = \"\"\n",
|
|
" asyncio.run(self._fetch_content())\n",
|
|
"\n",
|
|
" async def _fetch_content(self):\n",
|
|
" async with async_playwright() as p:\n",
|
|
" browser = None\n",
|
|
" try:\n",
|
|
" browser = await p.chromium.launch(headless=True)\n",
|
|
" page = await browser.new_page()\n",
|
|
"\n",
|
|
" # Increase timeout for navigation and other operations\n",
|
|
" await page.goto(self.url, timeout=60000) # Wait up to 60 seconds for navigation\n",
|
|
" print(f\"Accessing {self.url} with Playwright - goto()\")\n",
|
|
"\n",
|
|
" # You might need to adjust or add more specific waits\n",
|
|
" await page.wait_for_load_state('domcontentloaded', timeout=60000) # Wait for basic HTML\n",
|
|
" # await page.wait_for_load_state('networkidle', timeout=60000) # Wait for network activity to settle\n",
|
|
" await page.wait_for_selector('div.duration-short', timeout=60000) # instead of networkidle\n",
|
|
" await page.wait_for_selector('body', timeout=60000) # Wait for the body to be present\n",
|
|
" await asyncio.sleep(5) # Give a bit more time for final rendering\n",
|
|
"\n",
|
|
" content = await page.content()\n",
|
|
" soup = BeautifulSoup(content, 'html.parser')\n",
|
|
"\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",
|
|
" print(f\"Accessed {self.url} with Playwright\")\n",
|
|
"\n",
|
|
" except Exception as e:\n",
|
|
" print(f\"Error accessing {self.url} with Playwright: {e}\")\n",
|
|
" finally:\n",
|
|
" if browser:\n",
|
|
" await browser.close()\n",
|
|
"\n",
|
|
"display_summary(summarize(WebsitePlaywright(\"https://openai.com/\")))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "00743dac-0e70-45b7-879a-d7293a6f68a6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Step 1: Create your prompts\n",
|
|
"\n",
|
|
"system_prompt = \"You are a professional assistant. Review this conversation and provide a comprehensive summary. Also, suggest how much better the converation could have gone:\"\n",
|
|
"user_prompt = \"\"\"\n",
|
|
"\n",
|
|
"Dear Email Contact,\n",
|
|
"\n",
|
|
"I hope this message finds you well.\n",
|
|
"I would like to share that I have proficiency in front-end design tools, particularly Figma, react and Angular. At this stage, I am keenly interested in finding opportunities to apply these skills professionally.\n",
|
|
"\n",
|
|
"If you are aware of any companies, projects, or platforms seeking enterprise in front-end design, I would be grateful for any advice or recommendations you might kindly provide.\n",
|
|
"\n",
|
|
"Thank you very much for your time and consideration.\n",
|
|
"\n",
|
|
"Hello Job Seeker,\n",
|
|
"\n",
|
|
"I hope you are doing well.\n",
|
|
"\n",
|
|
"The last role (3 months gig) I saw was looking for a junior PHP Developer. Does your CV include that?\n",
|
|
"\n",
|
|
"Hello Email Contact,\n",
|
|
"Thank you for your feedback.\n",
|
|
"Yes my CV has PHP as one of my skill set. Can I share it with you?\n",
|
|
"\n",
|
|
"Email Contact: They said \"It's late. Interviews were on Monday\"\n",
|
|
"\n",
|
|
"Hello Email Contact\n",
|
|
"\n",
|
|
"Thanks for the update. When you hear of any opportunity please let me know.\n",
|
|
"\n",
|
|
"Email Contact: For now, check out https://refactory.academy/courses/refactory-apprenticeship/\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",
|
|
"# Step 4: print the result\n",
|
|
"\n",
|
|
"print(response.choices[0].message.content)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4b583226-9b13-4990-863a-86517a5ccfec",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# To perform summaries using a model running locally\n",
|
|
"import ollama\n",
|
|
"\n",
|
|
"# OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
|
|
"# HEADERS = {\"Content-Type\": \"application/json\"}\n",
|
|
"MODEL = \"llama3.2\"\n",
|
|
"\n",
|
|
"def summarize_with_local_model(url):\n",
|
|
" website = Website(url)\n",
|
|
" messages = messages_for(website)\n",
|
|
" response = ollama.chat(\n",
|
|
" model=MODEL,\n",
|
|
" messages=messages,\n",
|
|
" stream=False # just get the results, don't stream them\n",
|
|
" )\n",
|
|
" return response['message']['content']\n",
|
|
"\n",
|
|
"display(Markdown(summarize_with_local_model(\"https://rwothoromo.wordpress.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": "3.11.7"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|