Merge pull request #332 from jstoops/community-contributions-branch
Added my contributions to week 1, 2, and 5 community-contributions - RecursiveCharacterTextSplitter
This commit is contained in:
Ed Donner
GitHub
369
week1/community-contributions/day1-selenium-simple-jds.ipynb
Normal file
369
week1/community-contributions/day1-selenium-simple-jds.ipynb
Normal file
@@ -0,0 +1,369 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "83bbedd0-eb58-48de-992e-484071b10104",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Web Scraper with JavaScript Support\n",
|
||||
"Uses day1-webscraping-selenium-for-javascript.ipynb solution simplified so easy to run.\n",
|
||||
"\n",
|
||||
"## Install dependencies\n",
|
||||
"Uncomment and run once"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f2d91971-9dd0-4714-8ec7-f1fb25f95140",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install selenium\n",
|
||||
"# !pip install undetected-chromedriver\n",
|
||||
"# !ollama pull llama3.2"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "967258fe-3296-464c-962d-2bcf821eae67",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Import required dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fe8a87c8-0475-45a1-8ca2-fb9059e5470b",
|
||||
"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",
|
||||
"import undetected_chromedriver as uc\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",
|
||||
"import time\n",
|
||||
"from bs4 import BeautifulSoup\n",
|
||||
"\n",
|
||||
"# If you get an error running this cell, then please head over to the troubleshooting notebook!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "df60545e-2ab6-4e37-b41c-27ddf2affb92",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Run setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a3846089-efa2-4602-8bc3-5f6f4945de64",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chrome_path = \"C:/Program Files/Google/Chrome/Application/chrome.exe\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b835812d-3692-4192-abc4-15fc463bd08f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Load environment variables in a file called .env\n",
|
||||
"\n",
|
||||
"load_dotenv()\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": "acb89abb-dcee-4da6-98f8-e339d258f2a4",
|
||||
"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, or try the below line instead:\n",
|
||||
"# openai = OpenAI(api_key=\"your-key-here-starting-sk-proj-\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e860e963-e7a1-4888-a4b9-db9c24bb9a6e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create Prompts"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d4933c36-db8a-4333-8f81-e9db7ba41287",
|
||||
"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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "17cfab59-304d-4d2f-b324-c388d9e87fca",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create Functions"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ca5e96e0-4d8f-49de-a608-a735a5b23b1a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Setup for how OpenAI expects to receive messages in a particular structure\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",
|
||||
"# Use Selenium and chrome to scrape website\n",
|
||||
"class WebsiteCrawler:\n",
|
||||
" def __init__(self, url, wait_time=20, chrome_binary_path=None):\n",
|
||||
" \"\"\"\n",
|
||||
" Initialize the WebsiteCrawler using Selenium to scrape JavaScript-rendered content.\n",
|
||||
" \"\"\"\n",
|
||||
" self.url = url\n",
|
||||
" self.wait_time = wait_time\n",
|
||||
"\n",
|
||||
" options = uc.ChromeOptions()\n",
|
||||
" options.add_argument(\"--disable-gpu\")\n",
|
||||
" options.add_argument(\"--no-sandbox\")\n",
|
||||
" options.add_argument(\"--disable-dev-shm-usage\")\n",
|
||||
" options.add_argument(\"--disable-blink-features=AutomationControlled\")\n",
|
||||
" options.add_argument(\"start-maximized\")\n",
|
||||
" options.add_argument(\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",
|
||||
" if chrome_binary_path:\n",
|
||||
" options.binary_location = chrome_binary_path\n",
|
||||
"\n",
|
||||
" self.driver = uc.Chrome(options=options)\n",
|
||||
"\n",
|
||||
" try:\n",
|
||||
" # Load the URL\n",
|
||||
" self.driver.get(url)\n",
|
||||
"\n",
|
||||
" # Wait for Cloudflare or similar checks\n",
|
||||
" time.sleep(10)\n",
|
||||
"\n",
|
||||
" # Ensure the main content is loaded\n",
|
||||
" WebDriverWait(self.driver, self.wait_time).until(\n",
|
||||
" EC.presence_of_element_located((By.TAG_NAME, \"main\"))\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Extract the main content\n",
|
||||
" main_content = self.driver.find_element(By.CSS_SELECTOR, \"main\").get_attribute(\"outerHTML\")\n",
|
||||
"\n",
|
||||
" # Parse with BeautifulSoup\n",
|
||||
" soup = BeautifulSoup(main_content, \"html.parser\")\n",
|
||||
" self.title = self.driver.title if self.driver.title else \"No title found\"\n",
|
||||
" self.text = soup.get_text(separator=\"\\n\", strip=True)\n",
|
||||
"\n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"Error occurred: {e}\")\n",
|
||||
" self.title = \"Error occurred\"\n",
|
||||
" self.text = \"\"\n",
|
||||
"\n",
|
||||
" finally:\n",
|
||||
" self.driver.quit()\n",
|
||||
"\n",
|
||||
"def new_summary(url, chrome_path):\n",
|
||||
" web = WebsiteCrawler(url, 30, chrome_path)\n",
|
||||
" response = openai.chat.completions.create(\n",
|
||||
" model = \"gpt-4o-mini\",\n",
|
||||
" messages = messages_for(web)\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" web_summary = response.choices[0].message.content\n",
|
||||
" \n",
|
||||
" return display(Markdown(web_summary))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "20a8a14b-0a29-4f74-a591-d587b965409b",
|
||||
"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",
|
||||
"# Setup for how OpenAI expects to receive messages in a particular structure\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",
|
||||
"# Use Selenium and chrome to scrape website\n",
|
||||
"class WebsiteCrawler:\n",
|
||||
" def __init__(self, url, wait_time=20, chrome_binary_path=None):\n",
|
||||
" \"\"\"\n",
|
||||
" Initialize the WebsiteCrawler using Selenium to scrape JavaScript-rendered content.\n",
|
||||
" \"\"\"\n",
|
||||
" self.url = url\n",
|
||||
" self.wait_time = wait_time\n",
|
||||
"\n",
|
||||
" options = uc.ChromeOptions()\n",
|
||||
" options.add_argument(\"--disable-gpu\")\n",
|
||||
" options.add_argument(\"--no-sandbox\")\n",
|
||||
" options.add_argument(\"--disable-dev-shm-usage\")\n",
|
||||
" options.add_argument(\"--disable-blink-features=AutomationControlled\")\n",
|
||||
" options.add_argument(\"start-maximized\")\n",
|
||||
" options.add_argument(\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",
|
||||
" if chrome_binary_path:\n",
|
||||
" options.binary_location = chrome_binary_path\n",
|
||||
"\n",
|
||||
" self.driver = uc.Chrome(options=options)\n",
|
||||
"\n",
|
||||
" try:\n",
|
||||
" # Load the URL\n",
|
||||
" self.driver.get(url)\n",
|
||||
"\n",
|
||||
" # Wait for Cloudflare or similar checks\n",
|
||||
" time.sleep(10)\n",
|
||||
"\n",
|
||||
" # Ensure the main content is loaded\n",
|
||||
" WebDriverWait(self.driver, self.wait_time).until(\n",
|
||||
" EC.presence_of_element_located((By.TAG_NAME, \"main\"))\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" # Extract the main content\n",
|
||||
" main_content = self.driver.find_element(By.CSS_SELECTOR, \"main\").get_attribute(\"outerHTML\")\n",
|
||||
"\n",
|
||||
" # Parse with BeautifulSoup\n",
|
||||
" soup = BeautifulSoup(main_content, \"html.parser\")\n",
|
||||
" self.title = self.driver.title if self.driver.title else \"No title found\"\n",
|
||||
" self.text = soup.get_text(separator=\"\\n\", strip=True)\n",
|
||||
"\n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"Error occurred: {e}\")\n",
|
||||
" self.title = \"Error occurred\"\n",
|
||||
" self.text = \"\"\n",
|
||||
"\n",
|
||||
" finally:\n",
|
||||
" self.driver.quit()\n",
|
||||
"\n",
|
||||
"def new_summary(url, chrome_path):\n",
|
||||
" web = WebsiteCrawler(url, 30, chrome_path)\n",
|
||||
" response = openai.chat.completions.create(\n",
|
||||
" model = \"gpt-4o-mini\",\n",
|
||||
" messages = messages_for(web)\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" web_summary = response.choices[0].message.content\n",
|
||||
" \n",
|
||||
" return display(Markdown(web_summary))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e5f974b3-e417-43a2-88f1-8db06096cd53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Scrape and Summarize Web Page"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "55f240cb-1fca-46bf-81d1-1beeea64439d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"url = \"https://www.canva.com/\"\n",
|
||||
"new_summary(url, chrome_path)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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
|
||||
}
|
||||
@@ -0,0 +1,379 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a98030af-fcd1-4d63-a36e-38ba053498fa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Snarky brochure"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d5b08506-dc8b-4443-9201-5f1848161363",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# imports\n",
|
||||
"# If these fail, please check you're running from an 'activated' environment with (llms) in the command prompt\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"import requests\n",
|
||||
"import json\n",
|
||||
"from typing import List\n",
|
||||
"from dotenv import load_dotenv\n",
|
||||
"from bs4 import BeautifulSoup\n",
|
||||
"from IPython.display import Markdown, display, update_display\n",
|
||||
"from openai import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Initialize and constants\n",
|
||||
"\n",
|
||||
"load_dotenv(override=True)\n",
|
||||
"api_key = os.getenv('OPENAI_API_KEY')\n",
|
||||
"\n",
|
||||
"if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n",
|
||||
" print(\"API key looks good so far\")\n",
|
||||
"else:\n",
|
||||
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n",
|
||||
" \n",
|
||||
"MODEL = 'gpt-4o-mini'\n",
|
||||
"openai = OpenAI()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "106dd65e-90af-4ca8-86b6-23a41840645b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# A class to represent a Webpage\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",
|
||||
" A utility class to represent a Website that we have scraped, now with links\n",
|
||||
" \"\"\"\n",
|
||||
"\n",
|
||||
" def __init__(self, url):\n",
|
||||
" self.url = url\n",
|
||||
" response = requests.get(url, headers=headers)\n",
|
||||
" self.body = response.content\n",
|
||||
" soup = BeautifulSoup(self.body, 'html.parser')\n",
|
||||
" self.title = soup.title.string if soup.title else \"No title found\"\n",
|
||||
" if soup.body:\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",
|
||||
" else:\n",
|
||||
" self.text = \"\"\n",
|
||||
" links = [link.get('href') for link in soup.find_all('a')]\n",
|
||||
" self.links = [link for link in links if link]\n",
|
||||
"\n",
|
||||
" def get_contents(self):\n",
|
||||
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1771af9c-717a-4fca-bbbe-8a95893312c3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Link prompts\n",
|
||||
"### Multi-shot system prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6957b079-0d96-45f7-a26a-3487510e9b35",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n",
|
||||
"You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n",
|
||||
"such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n",
|
||||
"link_system_prompt += \"You should respond in JSON as in these examples:\"\n",
|
||||
"link_system_prompt += \"\"\"\n",
|
||||
"Example 1\n",
|
||||
"['https://my-company.com', 'https://my-company.com/about-me', 'https://www.linkedin.com/in/my-company/', 'mailto:joe.blog@gmail.com', 'https://my-company.com/news', '/case-studies', 'https://patents.google.com/patent/US20210049536A1/', 'https://my-company.com/workshop-ai']\n",
|
||||
"\n",
|
||||
" Links:\n",
|
||||
"{\n",
|
||||
" \"links\": [\n",
|
||||
" {\"type\": \"landing page\", \"url\": \"https://great-comps.com/about-me\"},\n",
|
||||
" {\"type\": \"about page\", \"url\": \"https://great-comps.com/about-me\"},\n",
|
||||
" {\"type\": \"news page\": \"url\": \"https://great-comps.com/news\"},\n",
|
||||
" {\"type\": \"case studies page\": \"url\": \"https://great-comps.com/case-studies\"},\n",
|
||||
" {\"type\": \"workshop page\": \"url\": \"https://great-comps.com/workshop-ai\"},\n",
|
||||
" ]\n",
|
||||
"}\n",
|
||||
"Example 2\n",
|
||||
"['https://www.acmeinc.com', '/#about', '/#projects', '/#experience', '/#skills', 'https://github.com/acmeinc']\n",
|
||||
"\n",
|
||||
" Links:\n",
|
||||
"{\n",
|
||||
" \"links\": [\n",
|
||||
" {\"type\": \"landing page\", \"url\": \"https://www.acmeinc.com\"},\n",
|
||||
" {\"type\": \"GitHub projects\": \"url\": \"https://github.com/acmeinc\"},\n",
|
||||
" ]\n",
|
||||
"}\n",
|
||||
"\"\"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b97e4068-97ed-4120-beae-c42105e4d59a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(link_system_prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "baf384bb-4577-4885-a445-dc8da232b1d9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### User prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "51174859-666a-43ad-9c34-5f082298d398",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Get links"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_links_user_prompt(website):\n",
|
||||
" user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n",
|
||||
" user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n",
|
||||
"Do not include Terms of Service, Privacy, email links.\\n\"\n",
|
||||
" user_prompt += \"Links (some might be relative links):\\n\"\n",
|
||||
" user_prompt += \"\\n\".join(website.links)\n",
|
||||
" return user_prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a29aca19-ca13-471c-a4b4-5abbfa813f69",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_links(url):\n",
|
||||
" website = Website(url)\n",
|
||||
" response = openai.chat.completions.create(\n",
|
||||
" model=MODEL,\n",
|
||||
" messages=[\n",
|
||||
" {\"role\": \"system\", \"content\": link_system_prompt},\n",
|
||||
" {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n",
|
||||
" ],\n",
|
||||
" response_format={\"type\": \"json_object\"}\n",
|
||||
" )\n",
|
||||
" result = response.choices[0].message.content\n",
|
||||
" return json.loads(result)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0d74128e-dfb6-47ec-9549-288b621c838c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create brochure"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_all_details(url):\n",
|
||||
" result = \"Landing page:\\n\"\n",
|
||||
" result += Website(url).get_contents()\n",
|
||||
" links = get_links(url)\n",
|
||||
" print(\"Found links:\", links)\n",
|
||||
" for link in links[\"links\"]:\n",
|
||||
" result += f\"\\n\\n{link['type']}\\n\"\n",
|
||||
" result += Website(link[\"url\"]).get_contents()\n",
|
||||
" return result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4b4d8ec1-4855-4c0e-afc0-33055e6b0a6d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Snarky system prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
||||
"# and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
||||
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n",
|
||||
"\n",
|
||||
"# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n",
|
||||
"\n",
|
||||
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
||||
"# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
||||
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n",
|
||||
"\n",
|
||||
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
||||
"and creates a short snarky, entertaining, pun loaded brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
||||
"Include details of company culture, customers and careers/jobs if you have the information.\"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c5766318-97cc-4442-bb9f-fa8c6998777e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### User prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d6e224b2-8ab0-476e-96c3-42763ad21f25",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Generate brochure in English"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_brochure_user_prompt(company_name, url):\n",
|
||||
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n",
|
||||
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n",
|
||||
" user_prompt += get_all_details(url)\n",
|
||||
" user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n",
|
||||
" return user_prompt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def create_brochure(company_name, url):\n",
|
||||
" response = openai.chat.completions.create(\n",
|
||||
" model=MODEL,\n",
|
||||
" messages=[\n",
|
||||
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
||||
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
|
||||
" ],\n",
|
||||
" )\n",
|
||||
" result = response.choices[0].message.content\n",
|
||||
" display(Markdown(result))\n",
|
||||
" return result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e093444a-9407-42ae-924a-145730591a39",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"brochure_text = create_brochure(\"HuggingFace\", \"https://huggingface.co\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "30415c72-d26a-454e-8900-f584977aca96",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Translate brochure to another language"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2331eb34-12bf-4e88-83f9-a48d97cc83ec",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"translation_sys_prompt = \"You are a language translator who is very good at translating business documents from \\\n",
|
||||
"English to any language. You preserve the formatting, tone and facts contained in the document.\"\n",
|
||||
"\n",
|
||||
"def translate_brochure(brochure, language):\n",
|
||||
" response = openai.chat.completions.create(\n",
|
||||
" model=MODEL,\n",
|
||||
" messages=[\n",
|
||||
" {\"role\": \"system\", \"content\": translation_sys_prompt},\n",
|
||||
" {\"role\": \"user\", \"content\": f\"Translate the following document into {language}: {brochure}\"}\n",
|
||||
" ],\n",
|
||||
" )\n",
|
||||
" result = response.choices[0].message.content\n",
|
||||
" display(Markdown(result))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "112beb4d-984b-4162-8d36-8cef79c351cc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"translate_brochure(brochure_text, \"Spanish\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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
|
||||
}
|
||||
221
week1/community-contributions/week1-tech-question-jds.ipynb
Normal file
221
week1/community-contributions/week1-tech-question-jds.ipynb
Normal file
@@ -0,0 +1,221 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# End of week 1 exercise\n",
|
||||
"\n",
|
||||
"To demonstrate your familiarity with OpenAI API, and also Ollama, build a tool that takes a technical question, \n",
|
||||
"and responds with an explanation. This is a tool that you will be able to use yourself during the course!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "c1070317-3ed9-4659-abe3-828943230e03",
|
||||
"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, update_display\n",
|
||||
"from openai import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# constants\n",
|
||||
"\n",
|
||||
"MODEL_GPT = 'gpt-4o-mini'\n",
|
||||
"MODEL_LLAMA = 'llama3.2'\n",
|
||||
"\n",
|
||||
"OLLAMA_API = \"http://localhost:11434/v1\"\n",
|
||||
"HEADERS = {\"Content-Type\": \"application/json\"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"API key looks good so far\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# set up environment\n",
|
||||
"\n",
|
||||
"load_dotenv(override=True)\n",
|
||||
"api_key = os.getenv('OPENAI_API_KEY')\n",
|
||||
"\n",
|
||||
"if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n",
|
||||
" print(\"API key looks good so far\")\n",
|
||||
"else:\n",
|
||||
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# here is the system prompt and payloads;\n",
|
||||
"\n",
|
||||
"system_prompt = \"\"\"\n",
|
||||
"You are an expert on LLMs and writing python code. You are able to answer complex questions with\n",
|
||||
"detailed answers and explain what every line of code does. You can refactor the code when asked.\n",
|
||||
"\"\"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "60ce7000-a4a5-4cce-a261-e75ef45063b4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Function to get answer, with streaming\n",
|
||||
"\n",
|
||||
"def llm_copilot(question, model):\n",
|
||||
" if 'llama' in model.lower():\n",
|
||||
" openai = OpenAI(base_url=OLLAMA_API, api_key='ollama')\n",
|
||||
" else:\n",
|
||||
" openai = OpenAI()\n",
|
||||
" \n",
|
||||
" stream = openai.chat.completions.create(\n",
|
||||
" model=model,\n",
|
||||
" messages=[\n",
|
||||
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
||||
" {\"role\": \"user\", \"content\": question}\n",
|
||||
" ],\n",
|
||||
" stream=True\n",
|
||||
" )\n",
|
||||
" response = \"\"\n",
|
||||
" display_handle = display(Markdown(\"\"), display_id=True)\n",
|
||||
" for chunk in stream:\n",
|
||||
" response += chunk.choices[0].delta.content or ''\n",
|
||||
" response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
|
||||
" update_display(Markdown(response), display_id=display_handle.display_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/markdown": [
|
||||
"Here's a revised version of your code:\n",
|
||||
"\n",
|
||||
"python\n",
|
||||
"if 'llama' in model.lower():\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"OR if you want to keep the original style, you can modify it as follows:\n",
|
||||
"\n",
|
||||
"python\n",
|
||||
"if model.split('.')[-1] == 'llama3.2':\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"In this second example, we use string indexing (`-1`) to get the last part of the `model` string after splitting at the dot (`.`) character.\n",
|
||||
"\n",
|
||||
"The first revised version uses Python's built-in string method `lower()` to convert `model` to lowercase and then checks if 'llama' is present in it. It returns True if the text contains \"llama\", otherwise, it will return False. \n",
|
||||
"\n",
|
||||
"However, both of these codes are using lazy evaluation, which means if you do this check inside a loop:\n",
|
||||
"\n",
|
||||
"python\n",
|
||||
"for i in range(100):\n",
|
||||
" print('llama')\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Python will use 'a' instead of 'llame' most of the time until `i == 98` because it has to wait for the condition to be met (and also does some lookup and look-around). If you want a case-insensitive search without this slowness, consider using a regular expression as shown below\n",
|
||||
"\n",
|
||||
"python\n",
|
||||
"import re\n",
|
||||
"\n",
|
||||
"if re.search(r' llama.', model):\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"And if you still want that specific code structure, then use `replace` function as follows:\n",
|
||||
"\n",
|
||||
"python\n",
|
||||
"model = model.replace('llama', '')\n",
|
||||
"if model == '3.2':\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Markdown object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"None\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Ask question\n",
|
||||
"question = \"\"\"\n",
|
||||
"Change this code to check for just the 'llama' portion of text instead of the entire string:\n",
|
||||
"if model == 'llama3.2':\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"print(llm_copilot(question, MODEL_LLAMA))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1a4026cd-8967-4961-b26b-e3997307c4ba",
|
||||
"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
|
||||
}
|
||||
Reference in New Issue
Block a user