From ae9222e3ef5b9bb1602fac6fbe80b736fe9e4ef8 Mon Sep 17 00:00:00 2001 From: Dheeraj Maddi Date: Tue, 15 Apr 2025 23:34:52 -0500 Subject: [PATCH 1/3] Added Selenium implementation for web scraping --- .../day1_selenium_implementation.ipynb | 271 ++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 week1/community-contributions/day1_selenium_implementation.ipynb diff --git a/week1/community-contributions/day1_selenium_implementation.ipynb b/week1/community-contributions/day1_selenium_implementation.ipynb new file mode 100644 index 0000000..fb6e3bf --- /dev/null +++ b/week1/community-contributions/day1_selenium_implementation.ipynb @@ -0,0 +1,271 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "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": "code", + "execution_count": null, + "id": "7b87cadb-d513-4303-baee-a37b6f938e4d", + "metadata": {}, + "outputs": [], + "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": null, + "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": "code", + "execution_count": null, + "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": 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": "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": "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": "acbb92b2-b625-4a37-b03a-09dc8f06b222", + "metadata": {}, + "outputs": [], + "source": [ + "!pip install selenium" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d6448a12-6aa1-4dd1-aaf1-c8a3a3c3ecb0", + "metadata": {}, + "outputs": [], + "source": [ + "!pip install webdriver-manager" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f4484fcf-8b39-4c3f-9674-37970ed71988", + "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", + "# Import necessary modules\n", + "from selenium import webdriver\n", + "from selenium.webdriver.chrome.options import Options\n", + "from selenium.webdriver.chrome.service import Service\n", + "from webdriver_manager.chrome import ChromeDriverManager\n", + "from bs4 import BeautifulSoup\n", + "import time\n", + "\n", + "class ScrapeWebsite:\n", + " def __init__(self, url):\n", + " \"\"\"\n", + " Create this Website object from the given URL using Selenium + BeautifulSoup\n", + " Supports JavaScript-heavy and normal websites uniformly.\n", + " \"\"\"\n", + " self.url = url\n", + "\n", + " # Configure headless Chrome\n", + " options = Options()\n", + " options.add_argument('--headless')\n", + " options.add_argument('--no-sandbox')\n", + " options.add_argument('--disable-dev-shm-usage')\n", + "\n", + " # Use webdriver-manager to manage ChromeDriver\n", + " service = Service(ChromeDriverManager().install())\n", + "\n", + " # Initialize the Chrome WebDriver with the service and options\n", + " driver = webdriver.Chrome(service=service, options=options)\n", + "\n", + " # Start Selenium WebDriver\n", + " driver.get(url)\n", + "\n", + " # Wait for JS to load (adjust as needed)\n", + " time.sleep(3)\n", + "\n", + " # Fetch the page source after JS execution\n", + " page_source = driver.page_source\n", + " driver.quit()\n", + "\n", + " # Parse the HTML content with BeautifulSoup\n", + " soup = BeautifulSoup(page_source, 'html.parser')\n", + "\n", + " # Extract title\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + "\n", + " # Remove unnecessary elements\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + "\n", + " # Extract the main text\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f576f485-60c0-4539-bfb3-79d821ebefa4", + "metadata": {}, + "outputs": [], + "source": [ + "def summarize_js_website(url):\n", + " website = ScrapeWebsite(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": null, + "id": "00ac3659-e4f0-4b64-8041-ba35bfa2c4c9", + "metadata": {}, + "outputs": [], + "source": [ + "summary = summarize_js_website(\"https://dheerajmaddi.netlify.app/\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d526136e-9960-4f09-aad0-32f8c11de0ac", + "metadata": {}, + "outputs": [], + "source": [ + "display(Markdown(summary))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bcf1fd75-9964-4223-bcda-f2794bc9f7af", + "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 +} From 23da4aedf563dfa7ae239ca0482492ac12957ad9 Mon Sep 17 00:00:00 2001 From: Dheeraj Maddi Date: Tue, 15 Apr 2025 23:38:26 -0500 Subject: [PATCH 2/3] Added Selenium implementation for web scraping --- .../community-contributions/day1_selenium_implementation.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/week1/community-contributions/day1_selenium_implementation.ipynb b/week1/community-contributions/day1_selenium_implementation.ipynb index fb6e3bf..7072134 100644 --- a/week1/community-contributions/day1_selenium_implementation.ipynb +++ b/week1/community-contributions/day1_selenium_implementation.ipynb @@ -113,7 +113,7 @@ "\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", + "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" From 5b6402534bd23e0b0330e6f0d1ff5201f6a43a53 Mon Sep 17 00:00:00 2001 From: Dheeraj Maddi Date: Wed, 16 Apr 2025 18:55:58 -0500 Subject: [PATCH 3/3] Completed Exercise-1 on Day-2: Implementation for web scraping summarization using Ollama --- ...xercise_ollama_website_summarization.ipynb | 266 ++++++++++++++++++ 1 file changed, 266 insertions(+) create mode 100644 week1/community-contributions/day2_exercise_ollama_website_summarization.ipynb diff --git a/week1/community-contributions/day2_exercise_ollama_website_summarization.ipynb b/week1/community-contributions/day2_exercise_ollama_website_summarization.ipynb new file mode 100644 index 0000000..f9d4ebc --- /dev/null +++ b/week1/community-contributions/day2_exercise_ollama_website_summarization.ipynb @@ -0,0 +1,266 @@ +{ + "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": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

Just before we get to the assignment --

\n", + " 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.
\n", + " https://edwarddonner.com/2024/11/13/llm-engineering-resources/
\n", + " Please keep this bookmarked, and I'll continue to add more useful links there over time.\n", + "
\n", + "
" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9cc85216-f6e4-436e-b6c1-976c8f2d1152", + "metadata": {}, + "outputs": [], + "source": [ + "!pip install webdriver-manager\n", + "!pip install selenium" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "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\n", + "import ollama\n", + "from openai import OpenAI\n", + "from selenium import webdriver\n", + "from selenium.webdriver.chrome.options import Options\n", + "from selenium.webdriver.chrome.service import Service\n", + "from webdriver_manager.chrome import ChromeDriverManager\n", + "import time" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "29ddd15d-a3c5-4f4e-a678-873f56162724", + "metadata": {}, + "outputs": [], + "source": [ + "# Constants\n", + "MODEL = \"llama3.2\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "479ff514-e8bd-4985-a572-2ea28bb4fa40", + "metadata": {}, + "outputs": [], + "source": [ + "# Let's just make sure the model is loaded\n", + "\n", + "!ollama pull llama3.2" + ] + }, + { + "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": "markdown", + "id": "a4704e10-f5fb-4c15-a935-f046c06fb13d", + "metadata": {}, + "source": [ + "## Alternative approach - using OpenAI python library to connect to Ollama" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "23057e00-b6fc-4678-93a9-6b31cb704bff", + "metadata": {}, + "outputs": [], + "source": [ + "# There's actually an alternative approach that some people might prefer\n", + "# You can use the OpenAI client python library to call Ollama:\n", + "\n", + "\n", + "ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')" + ] + }, + { + "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; use either of the above approaches." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8251b6a5-7b43-42b9-84a9-4a94b6bdb933", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "class ScrapeWebsite:\n", + " def __init__(self, url):\n", + " \"\"\"\n", + " Create this Website object from the given URL using Selenium + BeautifulSoup\n", + " Supports JavaScript-heavy and normal websites uniformly.\n", + " \"\"\"\n", + " self.url = url\n", + "\n", + " # Configure headless Chrome\n", + " options = Options()\n", + " options.add_argument('--headless')\n", + " options.add_argument('--no-sandbox')\n", + " options.add_argument('--disable-dev-shm-usage')\n", + "\n", + " # Use webdriver-manager to manage ChromeDriver\n", + " service = Service(ChromeDriverManager().install())\n", + "\n", + " # Initialize the Chrome WebDriver with the service and options\n", + " driver = webdriver.Chrome(service=service, options=options)\n", + "\n", + " # Start Selenium WebDriver\n", + " driver.get(url)\n", + "\n", + " # Wait for JS to load (adjust as needed)\n", + " time.sleep(3)\n", + "\n", + " # Fetch the page source after JS execution\n", + " page_source = driver.page_source\n", + " driver.quit()\n", + "\n", + " # Parse the HTML content with BeautifulSoup\n", + " soup = BeautifulSoup(page_source, 'html.parser')\n", + "\n", + " # Extract title\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + "\n", + " # Remove unnecessary elements\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + "\n", + " # Extract the main text\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6de38216-6d1c-48c4-877b-86d403f4e0f8", + "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.\"\n", + "\n", + "# 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\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", + "# And now: call the OpenAI API. You will get very familiar with this!\n", + "\n", + "def summarize(url):\n", + " website = ScrapeWebsite(url)\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": null, + "id": "5dbf8d5c-a42a-4a72-b3a4-c75865b841bb", + "metadata": {}, + "outputs": [], + "source": [ + "summary = summarize(\"https://edwarddonner.com/2024/11/13/llm-engineering-resources/\")\n", + "display(Markdown(summary))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4ddfacdc-b16a-4999-9ff2-93ed19600d24", + "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 +}