1 changed files with 171 additions and 0 deletions
@ -0,0 +1,171 @@ |
|||||||
|
{ |
||||||
|
"cells": [ |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "3a601886-67ac-49a2-95f6-c5b69d372a1c", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Constants\n", |
||||||
|
"HEADERS = {\"Content-Type\": \"application/json\"}\n", |
||||||
|
"MODEL = \"llama3.2\"" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "3b23d779-ae31-4b66-a4cd-8f6e06079a21", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Imports\n", |
||||||
|
"import ollama\n", |
||||||
|
"import os\n", |
||||||
|
"import requests\n", |
||||||
|
"from openai import OpenAI\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": null, |
||||||
|
"id": "c727418f-39b5-4743-99be-09f2da7896d5", |
||||||
|
"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": "6ec51fb5-6e98-479a-95f6-00618bc548d1", |
||||||
|
"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": null, |
||||||
|
"id": "bb3cd0c6-118b-4795-be3b-4b5d945305a2", |
||||||
|
"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": null, |
||||||
|
"id": "ee8118f0-6aca-40ee-9b80-df170465ab54", |
||||||
|
"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": null, |
||||||
|
"id": "acefe92a-8c9b-46f6-a6df-1e7c7f3b9d26", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def summarize(url):\n", |
||||||
|
" website = Website(url)\n", |
||||||
|
" messages = messages_for(website)\n", |
||||||
|
" response = ollama.chat(model=MODEL, messages=messages)\n", |
||||||
|
" return response['message']['content']" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "2a96ba84-6da4-49f1-ac50-79e8fa78046f", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def display_summary(url):\n", |
||||||
|
" summary = summarize(url)\n", |
||||||
|
" display(Markdown(summary))" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "3459b7a6-6f68-41e5-9bd4-4ac44807c636", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"display_summary(\"https://www.mendozacode.io\")" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "f3c85932-87a5-4acc-8161-1cc7129a660e", |
||||||
|
"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 |
||||||
|
} |
Loading…
Reference in new issue