You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

240 lines
6.3 KiB

{
"cells": [
{
"cell_type": "markdown",
"id": "9964872b-225d-4ced-93e4-fc5b279ec2ed",
"metadata": {},
"source": [
"# Webpage English summarizer with user inputs (url, ollama-based LLM) "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e49d399-d18c-4c91-8abc-cf3289e11e2f",
"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 ollama, time\n",
"from tqdm import tqdm"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "46e7d809-248d-41b8-80e1-36b210041581",
"metadata": {},
"outputs": [],
"source": [
"# Define system prompt.\n",
"\n",
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n",
"and provides a detailed summary, ignoring text that might be navigation related. \\\n",
"Respond in markdown, in English.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e8bf237f-591f-4c32-9415-5d5d4e2522b8",
"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 detailed 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": "7d39ee6d-c670-41ba-a0b8-debd55bda8e3",
"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": "code",
"execution_count": null,
"id": "43e28ff5-2def-4a47-acdd-2e06c0666956",
"metadata": {},
"outputs": [],
"source": [
"# Constants\n",
"\n",
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
"HEADERS = {\"Content-Type\": \"application/json\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "32f4f481-81a3-479d-817b-4e754d9af46d",
"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 = HEADERS\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": "f81cfd17-8208-4192-a59f-485ff3ea74e4",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the ollama API wrapper and return the relevant component of the response\n",
"\n",
"def summarize(url):\n",
" website = Website(url)\n",
" response = ollama.chat(\n",
" model=MODEL,\n",
" messages = messages_for(website)\n",
" )\n",
" return response['message']['content']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7a9eedc6-2183-473d-84ca-b10d40e2a1e6",
"metadata": {},
"outputs": [],
"source": [
"# Ask the user the name of the url address\n",
"\n",
"url= str(input(\"\"\"\n",
"Please provide a valid url address:\n",
"https://\"\"\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5d012de2-0ef2-43db-9f51-fc7f989c3642",
"metadata": {},
"outputs": [],
"source": [
"# Ask the user to select a valid model\n",
"\n",
"MODEL= str(input(\"\"\"\n",
"Please select a LLM:\n",
"(examples: llama3.2, deepseek-r1:1.5b)\n",
"\"\"\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ac8c02e-4a62-448b-a231-8c6f65891811",
"metadata": {},
"outputs": [],
"source": [
"# Let's just make sure the model is loaded\n",
"\n",
"!ollama pull {MODEL}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0544541f-11a8-4eb7-8eb6-bc032ed6d0d1",
"metadata": {},
"outputs": [],
"source": [
"print('url: https://{0}\\nModel= {1}'.format(url, MODEL))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "45518950-f2c9-43af-b897-4fe8fe48dfd8",
"metadata": {},
"outputs": [],
"source": [
"summary = summarize('https://'+ url)\n",
"for summ in tqdm(summary):\n",
" time.sleep(0.01)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "02c0c15e-216d-47c7-843d-ac27af02820b",
"metadata": {},
"outputs": [],
"source": [
"display(Markdown(summary))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "985a3689-5827-4b15-b8d5-276f9b292afd",
"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
}