From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
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.
233 lines
7.1 KiB
233 lines
7.1 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "1b8f7ac7-7089-427a-8f63-57211da7e691", |
|
"metadata": {}, |
|
"source": [ |
|
"## Summarizing Research Papers" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "641d5c00-ff09-4697-9c87-5de5df1469f8", |
|
"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": "1a6a2864-fd9d-43e2-b0ca-1476c0153077", |
|
"metadata": {}, |
|
"outputs": [], |
|
"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": null, |
|
"id": "340e3166-5aa7-4bcf-9cf0-e2fc776dc322", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"openai = OpenAI()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "73198fb7-581f-42ac-99a6-76c56c86248d", |
|
"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 Paper:\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": "3b39c3ad-d238-418e-9e6a-55a4fd717ebc", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"#Insert Paper URL\n", |
|
"res = Paper(\" \")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "83bc1eec-4187-4c6c-b188-3f72564351f1", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"system_prompt = \"\"\"You are a research paper summarizer. You take the url of the research paper and extract the following:\n", |
|
"1) Title and Author of the research paper.\n", |
|
"2) Year it was published it\n", |
|
"3) Objective or aim of the research to specify why the research was conducted\n", |
|
"4) Background or Introduction to explain the need to conduct this research or any topics the readers must have knowledge about\n", |
|
"5) Type of research/study/experiment to explain what kind of research it is.\n", |
|
"6) Methods or methodology to explain what the researchers did to conduct the research\n", |
|
"7) Results and key findings to explain what the researchers found\n", |
|
"8) Conclusion tells about the conclusions that can be drawn from this research including limitations and future direction\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "4aba1b51-9a72-4325-8c86-3968b9d3172e", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# A function that writes a User Prompt that asks for summaries of websites:\n", |
|
"\n", |
|
"def user_prompt_for(paper):\n", |
|
" user_prompt = f\"You are looking at a website titled {paper.title}\"\n", |
|
" user_prompt += \"\\nThe contents of this paper is as follows; \\\n", |
|
"please provide a short summary of this paper in markdown. \\\n", |
|
"If it includes additional headings, then summarize these too.\\n\\n\"\n", |
|
" user_prompt += paper.text\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "659cb3c4-8a02-493d-abe7-20da9219e358", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# See how this function creates exactly the format above\n", |
|
"def messages_for(paper):\n", |
|
" return [\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": user_prompt_for(paper)}\n", |
|
" ]" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "08ea1193-1bbb-40de-ba64-d02ffe109372", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"messages_for(res)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "e07d00e7-1b87-4ca8-a69d-4a206e34a2b2", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# And now: call the OpenAI API. You will get very familiar with this!\n", |
|
"\n", |
|
"def summarize(url):\n", |
|
" paper = Paper(url)\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model = \"gpt-4o-mini\",\n", |
|
" messages = messages_for(paper)\n", |
|
" )\n", |
|
" return response.choices[0].message.content" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "5c12df95-1700-47ee-891b-96b0a7227bdd", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# A function to display this nicely in the Jupyter output, using markdown\n", |
|
"\n", |
|
"def display_summary(url):\n", |
|
" summary = summarize(url)\n", |
|
" display(Markdown(summary))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "05cff05f-2b74-44a4-9dbd-57c08f8f56cb", |
|
"metadata": { |
|
"scrolled": true |
|
}, |
|
"outputs": [], |
|
"source": [ |
|
"# Insert Paper URL in the quotes below\n", |
|
"display_summary(\" \")" |
|
] |
|
} |
|
], |
|
"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 |
|
}
|
|
|