379 lines
12 KiB
Plaintext
379 lines
12 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "a98030af-fcd1-4d63-a36e-38ba053498fa",
|
|
"metadata": {},
|
|
"source": [
|
|
"# A full business solution\n",
|
|
"\n",
|
|
"Create a product that builds a Brochure for a company to be used for prospective clients, investors and potential recruits.\n",
|
|
"\n",
|
|
"We will be provided a company name and their primary website."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d5b08506-dc8b-4443-9201-5f1848161363",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\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()\n",
|
|
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\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",
|
|
"class Website:\n",
|
|
" url: str\n",
|
|
" title: str\n",
|
|
" body: str\n",
|
|
" links: List[str]\n",
|
|
"\n",
|
|
" def __init__(self, url):\n",
|
|
" self.url = url\n",
|
|
" response = requests.get(url)\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": "code",
|
|
"execution_count": null,
|
|
"id": "e30d8128-933b-44cc-81c8-ab4c9d86589a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"ed = Website(\"https://edwarddonner.com\")\n",
|
|
"print(ed.get_contents())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "1771af9c-717a-4fca-bbbe-8a95893312c3",
|
|
"metadata": {},
|
|
"source": [
|
|
"## First step: Have GPT-4o-mini figure out which links are relevant\n",
|
|
"\n",
|
|
"### Use a call to gpt-4o-mini to read the links on a webpage, and respond in structured JSON. \n",
|
|
"It should decide which links are relevant, and replace relative links such as \"/about\" with \"https://company.com/about\". \n",
|
|
"We will use \"one shot prompting\" in which we provide an example of how it should respond in the 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 this example:\"\n",
|
|
"link_system_prompt += \"\"\"\n",
|
|
"{\n",
|
|
" \"links\": [\n",
|
|
" {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n",
|
|
" {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n",
|
|
" ]\n",
|
|
"}\n",
|
|
"\"\"\""
|
|
]
|
|
},
|
|
{
|
|
"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": "6bcbfa78-6395-4685-b92c-22d592050fd7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(get_links_user_prompt(ed))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a29aca19-ca13-471c-a4b4-5abbfa813f69",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_links(url):\n",
|
|
" website = Website(url)\n",
|
|
" completion = 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 = completion.choices[0].message.content\n",
|
|
" return json.loads(result)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"get_links(\"https://anthropic.com\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "0d74128e-dfb6-47ec-9549-288b621c838c",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Second step: make the brochure!\n",
|
|
"\n",
|
|
"Assemble all the details into another prompt to GPT4-o"
|
|
]
|
|
},
|
|
{
|
|
"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": "code",
|
|
"execution_count": null,
|
|
"id": "5099bd14-076d-4745-baf3-dac08d8e5ab2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"print(get_all_details(\"https://anthropic.com\"))"
|
|
]
|
|
},
|
|
{
|
|
"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 line below for a more humorous brochure:\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"
|
|
]
|
|
},
|
|
{
|
|
"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[:20_000] # Truncate if more than 20,000 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))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e093444a-9407-42ae-924a-145730591a39",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"create_brochure(\"Anthropic\", \"https://anthropic.com\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Finally - a minor improvement\n",
|
|
"\n",
|
|
"With a small adjustment, we can change this so that the results stream back from OpenAI,\n",
|
|
"with the familiar typewriter animation"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bcb358a4-aa7f-47ec-b2bc-67768783dfe1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "51db0e49-f261-4137-aabe-92dd601f7725",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def stream_brochure(company_name, url):\n",
|
|
" stream = 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",
|
|
" stream=True\n",
|
|
" )\n",
|
|
" \n",
|
|
" response = \"\"\n",
|
|
" display_handle = display(Markdown(\"\"), display_id=True)\n",
|
|
" for chunk in stream:\n",
|
|
" response += chunk.choices[0].delta.content or ''\n",
|
|
" response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
|
|
" update_display(Markdown(response), display_id=display_handle.display_id)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"stream_brochure(\"Anthropic\", \"https://anthropic.com\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "fdb3f8d8-a3eb-41c8-b1aa-9f60686a653b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"stream_brochure(\"HuggingFace\", \"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bcf5168e-f1d9-4fa7-b372-daf16358e93c",
|
|
"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": "3.11.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|