203 lines
6.3 KiB
Plaintext
203 lines
6.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "5c527a13-459e-4a46-b00e-f2c5056de155",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Research Paper Summarizer with Text Highlighting"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "861a0be5-6da7-4f66-8f82-bc083a913f9f",
|
|
"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"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "74bf6765-53b6-457b-ac2d-0d1afa7fbf8f",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"API key found and looks good so far!\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Load environment variables in a file called .env\n",
|
|
"\n",
|
|
"load_dotenv(override=True)\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": 4,
|
|
"id": "227ed7af-d539-4c87-988b-80e6e049c863",
|
|
"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": "code",
|
|
"execution_count": 5,
|
|
"id": "dcaadf8b-456d-48ca-af9d-9f57d3414308",
|
|
"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": 6,
|
|
"id": "6315093f-be68-408e-a5e1-6a2e4ea675e8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def user_prompt_for(website):\n",
|
|
" user_prompt = f\"You are looking at an article 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",
|
|
"I'm also looking for complete statements containing the following keywords (if found): \\\n",
|
|
"'large circuit model', 'ChipGPT' \\n\\n\"\n",
|
|
" user_prompt += website.text\n",
|
|
" return user_prompt\n",
|
|
"\n",
|
|
"\n",
|
|
"article = Website(\"https://arxiv.org/html/2401.12224v1\")\n",
|
|
"# print(user_prompt_for(article))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "ff8a4112-f118-4866-b6cf-82675de0a38d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"system_prompt = \"You are an assistant that analyzes the contents of a scientific \\\n",
|
|
"article for a PhD student (who has to read a lot of papers and journals). The \\\n",
|
|
"user will provide the article website and keyword(s) they are looking to learn and \\\n",
|
|
"cite from. Your job is to summarize the paper and point out all the statements \\\n",
|
|
"containing the specific keyword(s) the user typed. \\\n",
|
|
"Respond in markdown.\"\n",
|
|
"\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",
|
|
" \n",
|
|
"#messages_for(article)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "b5e47bea-403d-48c3-ab9d-4d6adef83241",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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",
|
|
"\n",
|
|
"def display_summary(url):\n",
|
|
" summary = summarize(url)\n",
|
|
" display(Markdown(summary))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9f6ac1bc-5bc8-4daa-8174-d201400e517a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"display_summary(\"https://arxiv.org/html/2401.12224v1\")"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.13"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|