186 lines
5.2 KiB
Plaintext
186 lines
5.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fef36918-109d-41e3-8603-75ff81b42379",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Solution for exercise day 2 - slight modification: model is a parameter also - display_summary(\"deepseek-r1:1.5b\",\"https://yoururl\")\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b50349ac-93ea-496b-ae20-bd72a93bb138",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\n",
|
|
"\n",
|
|
"import requests\n",
|
|
"from bs4 import BeautifulSoup\n",
|
|
"from IPython.display import Markdown, display"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "edd073c7-8444-4a0d-b84e-4b2ed0ee7f35",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Constants\n",
|
|
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
|
|
"HEADERS = {\"Content-Type\": \"application/json\"}\n",
|
|
"#MODEL = \"llama3.2\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2e3a6e1a-e4c7-4448-9852-1b6ba2bd8d66",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# A class to represent a Webpage\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": "ae3752ca-3a97-4d6a-ac84-5b75ebfb50ed",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Define the system prompt \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": "48b5240f-7617-4e51-a320-cba9650bec84",
|
|
"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": "6f7d84f0-60f2-4cbf-b4d1-173a79fe3380",
|
|
"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": "25520a31-c857-4ed5-86da-50dfe5fab7bb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def summarize(model,url):\n",
|
|
" website = Website(url)\n",
|
|
" payload = {\n",
|
|
" \"model\": model,\n",
|
|
" \"messages\": messages_for(website),\n",
|
|
" \"stream\": False\n",
|
|
" }\n",
|
|
" response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n",
|
|
" return response.json()['message']['content']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "430776ed-8516-43a9-8a22-618d9080f2e1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# A function to display this nicely in the Jupyter output, using markdown\n",
|
|
"def display_summary(model,url):\n",
|
|
" summary = summarize(model,url)\n",
|
|
" display(Markdown(summary))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b2b05c1f-e4a2-4f65-bd6d-634d72e38b6e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#!ollama pull deepseek-r1:1.5b"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "01513f8a-15b7-4053-bfe4-44b36e5494d1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"display_summary(\"deepseek-r1:1.5b\",\"https://www.ipma.pt\")"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.12.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|