brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added compare-websites to community-contributions for week1

Browse Source
This commit is contained in:
Dan Palade
2025-04-24 15:12:12 -07:00
parent b8b2f766e5
commit f59bd64bb5
1 changed files with 293 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

293
week1/community-contributions/day1-compare-websites.ipynb Normal file
View File

@@ -0,0 +1,293 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "2c80b652-eadd-4d48-a512-d5945c0365d3",
"metadata": {},
"source": [
"# Compare websites"
]
},
{
"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 \n",
"\n",
"load_dotenv(override=True)\n",
"api_key = os.getenv('OPENAI_API_KEY')"
]
},
{
"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": "markdown",
"id": "2aa190e5-cb31-456a-96cc-db109919cd78",
"metadata": {},
"source": [
"## Website class"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c5e793b2-6775-426a-a139-4848291d0463",
"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": 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": "markdown",
"id": "d06e8d78-ce4c-4b05-aa8e-17050c82bb47",
"metadata": {},
"source": [
"## Website messages function"
]
},
{
"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": "16f49d46-bf55-4c3e-928f-68fc0bf715b0",
"metadata": {},
"source": [
"## Website summary"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "905b9919-aba7-45b5-ae65-81b3d1d78e34",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the OpenAI API. You will get very familiar with this!\n",
"\n",
"def summarize(url):\n",
" website = Website(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\n",
"\n",
"# A function to display this nicely in the Jupyter output, using markdown\n",
"\n",
"def display_summary(summary): \n",
" display(Markdown(summary))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d926d59-450e-4609-92ba-2d6f244f1342",
"metadata": {},
"outputs": [],
"source": [
"w1 = \"https://cnn.com\"\n",
"summary1 = summarize(w1)\n",
"display_summary(summary1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "45d83403-a24c-44b5-84ac-961449b4008f",
"metadata": {},
"outputs": [],
"source": [
"w2 = \"https://www.foxnews.com\"\n",
"summary2 = summarize(w2)\n",
"display_summary(summary2)"
]
},
{
"cell_type": "markdown",
"id": "0a51b45c-f3a6-4b0b-acfe-52957c04fd94",
"metadata": {},
"source": [
"## Comparison between two websites"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4b30d5a5-bbe5-499c-9392-0896440f80c7",
"metadata": {},
"outputs": [],
"source": [
"system_prompt_compare = \"\"\"You are a weblsite analyst that compares the summaries of two websites\n",
"and provides a compare and contrast bewtween the two. \n",
"Respond in markdown.\"\"\"\n",
"\n",
"def user_prompt_for_compare(summary1, summary2):\n",
" user_prompt = f\"You are asked to compare this summary of a website {summary1}\\n\\n\"\n",
" user_prompt += f\"\\nWith the summary of this second website {summary2}\\n\\n\"\n",
" user_prompt += \"please provide a short comparison of the two websites. \\\n",
"List the similarities and differences in bullet point format.\\n\\n\" \n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c5c9c955-840f-4c31-a1a7-b4872f77f3b4",
"metadata": {},
"outputs": [],
"source": [
"def messages_for_compare():\n",
" return [\n",
" {\"role\": \"system\", \"content\": system_prompt_compare},\n",
" {\"role\": \"user\", \"content\": user_prompt_for_compare(summary1, summary2)}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "56307d77-f207-48f1-b59a-e97f6a2a37dd",
"metadata": {},
"outputs": [],
"source": [
"def compare(): \n",
" response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages_for_compare()\n",
" )\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ae3140bb-ddad-43e2-b697-6d05ae541544",
"metadata": {},
"outputs": [],
"source": [
"display_summary(compare())"
]
}
],
"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
}