380 lines
13 KiB
Plaintext
380 lines
13 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "a98030af-fcd1-4d63-a36e-38ba053498fa",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Snarky brochure"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d5b08506-dc8b-4443-9201-5f1848161363",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\n",
|
|
"# If these fail, please check you're running from an 'activated' environment with (llms) in the command prompt\n",
|
|
"\n",
|
|
"import os\n",
|
|
"import requests\n",
|
|
"import json\n",
|
|
"from typing import List\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"from bs4 import BeautifulSoup\n",
|
|
"from IPython.display import Markdown, display, update_display\n",
|
|
"from openai import OpenAI"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Initialize and constants\n",
|
|
"\n",
|
|
"load_dotenv(override=True)\n",
|
|
"api_key = os.getenv('OPENAI_API_KEY')\n",
|
|
"\n",
|
|
"if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n",
|
|
" print(\"API key looks good so far\")\n",
|
|
"else:\n",
|
|
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n",
|
|
" \n",
|
|
"MODEL = 'gpt-4o-mini'\n",
|
|
"openai = OpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "106dd65e-90af-4ca8-86b6-23a41840645b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# A class to represent a Webpage\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",
|
|
" A utility class to represent a Website that we have scraped, now with links\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" def __init__(self, url):\n",
|
|
" self.url = url\n",
|
|
" response = requests.get(url, headers=headers)\n",
|
|
" self.body = response.content\n",
|
|
" soup = BeautifulSoup(self.body, 'html.parser')\n",
|
|
" self.title = soup.title.string if soup.title else \"No title found\"\n",
|
|
" if soup.body:\n",
|
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
|
|
" irrelevant.decompose()\n",
|
|
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
|
|
" else:\n",
|
|
" self.text = \"\"\n",
|
|
" links = [link.get('href') for link in soup.find_all('a')]\n",
|
|
" self.links = [link for link in links if link]\n",
|
|
"\n",
|
|
" def get_contents(self):\n",
|
|
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "1771af9c-717a-4fca-bbbe-8a95893312c3",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Link prompts\n",
|
|
"### Multi-shot system prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6957b079-0d96-45f7-a26a-3487510e9b35",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n",
|
|
"You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n",
|
|
"such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n",
|
|
"link_system_prompt += \"You should respond in JSON as in these examples:\"\n",
|
|
"link_system_prompt += \"\"\"\n",
|
|
"Example 1\n",
|
|
"['https://my-company.com', 'https://my-company.com/about-me', 'https://www.linkedin.com/in/my-company/', 'mailto:joe.blog@gmail.com', 'https://my-company.com/news', '/case-studies', 'https://patents.google.com/patent/US20210049536A1/', 'https://my-company.com/workshop-ai']\n",
|
|
"\n",
|
|
" Links:\n",
|
|
"{\n",
|
|
" \"links\": [\n",
|
|
" {\"type\": \"landing page\", \"url\": \"https://great-comps.com/about-me\"},\n",
|
|
" {\"type\": \"about page\", \"url\": \"https://great-comps.com/about-me\"},\n",
|
|
" {\"type\": \"news page\": \"url\": \"https://great-comps.com/news\"},\n",
|
|
" {\"type\": \"case studies page\": \"url\": \"https://great-comps.com/case-studies\"},\n",
|
|
" {\"type\": \"workshop page\": \"url\": \"https://great-comps.com/workshop-ai\"},\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"Example 2\n",
|
|
"['https://www.acmeinc.com', '/#about', '/#projects', '/#experience', '/#skills', 'https://github.com/acmeinc']\n",
|
|
"\n",
|
|
" Links:\n",
|
|
"{\n",
|
|
" \"links\": [\n",
|
|
" {\"type\": \"landing page\", \"url\": \"https://www.acmeinc.com\"},\n",
|
|
" {\"type\": \"GitHub projects\": \"url\": \"https://github.com/acmeinc\"},\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"\"\"\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b97e4068-97ed-4120-beae-c42105e4d59a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(link_system_prompt)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "baf384bb-4577-4885-a445-dc8da232b1d9",
|
|
"metadata": {},
|
|
"source": [
|
|
"### User prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "51174859-666a-43ad-9c34-5f082298d398",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Get links"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_links_user_prompt(website):\n",
|
|
" user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n",
|
|
" user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n",
|
|
"Do not include Terms of Service, Privacy, email links.\\n\"\n",
|
|
" user_prompt += \"Links (some might be relative links):\\n\"\n",
|
|
" user_prompt += \"\\n\".join(website.links)\n",
|
|
" return user_prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a29aca19-ca13-471c-a4b4-5abbfa813f69",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_links(url):\n",
|
|
" website = Website(url)\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": link_system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n",
|
|
" ],\n",
|
|
" response_format={\"type\": \"json_object\"}\n",
|
|
" )\n",
|
|
" result = response.choices[0].message.content\n",
|
|
" return json.loads(result)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "0d74128e-dfb6-47ec-9549-288b621c838c",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Create brochure"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_all_details(url):\n",
|
|
" result = \"Landing page:\\n\"\n",
|
|
" result += Website(url).get_contents()\n",
|
|
" links = get_links(url)\n",
|
|
" print(\"Found links:\", links)\n",
|
|
" for link in links[\"links\"]:\n",
|
|
" result += f\"\\n\\n{link['type']}\\n\"\n",
|
|
" result += Website(link[\"url\"]).get_contents()\n",
|
|
" return result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4b4d8ec1-4855-4c0e-afc0-33055e6b0a6d",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Snarky system prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
|
"# and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
|
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n",
|
|
"\n",
|
|
"# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n",
|
|
"\n",
|
|
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
|
"# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
|
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n",
|
|
"\n",
|
|
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
|
|
"and creates a short snarky, entertaining, pun loaded brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
|
|
"Include details of company culture, customers and careers/jobs if you have the information.\"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c5766318-97cc-4442-bb9f-fa8c6998777e",
|
|
"metadata": {},
|
|
"source": [
|
|
"### User prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d6e224b2-8ab0-476e-96c3-42763ad21f25",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Generate brochure in English"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_brochure_user_prompt(company_name, url):\n",
|
|
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n",
|
|
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n",
|
|
" user_prompt += get_all_details(url)\n",
|
|
" user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n",
|
|
" return user_prompt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def create_brochure(company_name, url):\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
|
|
" ],\n",
|
|
" )\n",
|
|
" result = response.choices[0].message.content\n",
|
|
" display(Markdown(result))\n",
|
|
" return result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e093444a-9407-42ae-924a-145730591a39",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"brochure_text = create_brochure(\"HuggingFace\", \"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "30415c72-d26a-454e-8900-f584977aca96",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Translate brochure to another language"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2331eb34-12bf-4e88-83f9-a48d97cc83ec",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"translation_sys_prompt = \"You are a language translator who is very good at translating business documents from \\\n",
|
|
"English to any language. You preserve the formatting, tone and facts contained in the document.\"\n",
|
|
"\n",
|
|
"def translate_brochure(brochure, language):\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": translation_sys_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": f\"Translate the following document into {language}: {brochure}\"}\n",
|
|
" ],\n",
|
|
" )\n",
|
|
" result = response.choices[0].message.content\n",
|
|
" display(Markdown(result))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "112beb4d-984b-4162-8d36-8cef79c351cc",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"translate_brochure(brochure_text, \"Spanish\")"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|