403 lines
13 KiB
Plaintext
403 lines
13 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9905f163-759f-474b-8f7a-7d14da0df44d",
|
|
"metadata": {},
|
|
"source": [
|
|
"### BUSINESS CHALLENGE: Using Multi-shot Prompting\n",
|
|
"#### Day 5\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": "a0895f24-65ff-4624-8ae0-15d2d400d8f0",
|
|
"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": "7794aa70-5962-4669-b86f-b53639f4f9ea",
|
|
"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": "63bf8631-2746-4255-bec1-522855d3e812",
|
|
"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": "1e7bb527-e769-4245-bb91-ae65e64593ff",
|
|
"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. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1ce303ae-b967-4261-aadc-02dafa54db4a",
|
|
"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": "d24a4c0c-a1d1-4897-b2a7-4128d25c2e08",
|
|
"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": "8103fc11-5bc0-41c4-8c97-502c9e96429c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_links(url): # 1st inference\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": "code",
|
|
"execution_count": null,
|
|
"id": "dc84a695-515d-4292-9a95-818f4fe3d20e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"huggingface = Website(\"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "91896908-1632-41fc-9b8b-39a7638d8dd1",
|
|
"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": "ab7c54e3-e654-4b1f-8671-09194b628aa0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_all_details(url): # 1st inference wrapper\n",
|
|
" result = \"Landing page:\\n\"\n",
|
|
" result += Website(url).get_contents()\n",
|
|
" links = get_links(url) # inference\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": "ea9f54d1-a248-4c56-a1de-6633193de5bf",
|
|
"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 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.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "13412c85-badd-4d79-a5ac-8283e4bb832f",
|
|
"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) # inference wrapper\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": "addc0047-ea73-4748-abc3-747ff343c134",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def create_brochure(company_name, url): # 2nd inference\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",
|
|
" return result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "82a3b61a-da26-4265-840a-0a93f81cd048",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"brochure_english = create_brochure(\"HuggingFace\", \"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5d165e3f-8fe2-4712-b098-d34d9fabe583",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"display(Markdown(brochure_english))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "107a2100-3f7d-4f16-8ba7-b5da602393c6",
|
|
"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": "26cbe9b5-3603-49a1-a676-75c7ddaacdb8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"stream_brochure(\"HuggingFace\", \"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c10d8189-7f79-4991-abc4-0764369b7d64",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Third step: Translate the entire brochure to Spanish"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "666817eb-1e8b-4fee-bbab-c0dbfe2ea7c0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"system_prompt = \"You are an assistant that analyzes the contents of a brochure \\\n",
|
|
"and translates to Spanish. Respond in markdown.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c48adb12-bc3c-48f9-ab38-b7ca895195f6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def translate_user_prompt(company_name, url):\n",
|
|
" user_prompt = f\"Please translate the following brochure content to Spanish\\n\"\n",
|
|
" user_prompt += create_brochure(company_name, url) # inference wrapper\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": "b92b61ac-3be3-4e84-9000-ec8233697b81",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"translate_user_prompt(\"HuggingFace\", \"https://huggingface.co\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6bfd04f4-4381-4730-ac5d-c9fa02f906df",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def translate_brochure(): # 3rd inference\n",
|
|
" stream = openai.chat.completions.create(\n",
|
|
" model=MODEL,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": translate_user_prompt(\"HuggingFace\", \"https://huggingface.co\")}\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": "bb78ed28-9ecd-4c08-ae96-d7473cbc97dd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"translate_brochure()"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|