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.
460 lines
14 KiB
460 lines
14 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "e71d7ff9-c27a-4602-9230-856626b1de07", |
|
"metadata": {}, |
|
"source": [ |
|
"# Company Brochure Generator UI\n", |
|
"Generates a brochure for a company website, after scraping the website and pages linked with that page, based on the provided company URL. \n", |
|
"Enables users to \n", |
|
"- Choose a model type (Llama 3.2, Claude, GPT)-\n", |
|
"- Choose the tone preference\n", |
|
"- Choose the target audience" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "de9b59b9-8673-42e7-8849-62fe30f56711", |
|
"metadata": {}, |
|
"source": [ |
|
"#### Imports, Keys, Instantiation" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 38, |
|
"id": "39fd7fed-b215-4037-bd6e-7e1af1b83897", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"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\n", |
|
"import anthropic\n", |
|
"import gradio as gr" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 15, |
|
"id": "0bf24357-1d77-4721-9d5a-f99827b2158c", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"OpenAI API Key exists and begins sk-proj-\n", |
|
"Anthropic API Key exists and begins sk-ant-\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# Load environment variables in a file called .env\n", |
|
"\n", |
|
"load_dotenv(override=True)\n", |
|
"openai_api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n", |
|
"\n", |
|
"if openai_api_key:\n", |
|
" print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n", |
|
"else:\n", |
|
" print(\"OpenAI API Key not set\")\n", |
|
" \n", |
|
"if anthropic_api_key:\n", |
|
" print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n", |
|
"else:\n", |
|
" print(\"Anthropic API Key not set\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 20, |
|
"id": "1afc12e1-02c1-4394-b589-19cd08d2a8bb", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Define models\n", |
|
"CLAUDE_MODEL = \"claude-3-haiku-20240307\"\n", |
|
"GPT_MODEL = \"gpt-4o-mini\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 17, |
|
"id": "d5d79a69-0a39-4ab4-aaf8-bc591bce0536", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Creating instances\n", |
|
"claude = anthropic.Anthropic()\n", |
|
"openai = OpenAI()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "1d3369bc-b751-4f4d-a288-d7d81c384e67", |
|
"metadata": {}, |
|
"source": [ |
|
"#### Web Scraper" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 8, |
|
"id": "fafe1074-fbf4-47cc-80dc-34413a447977", |
|
"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": "code", |
|
"execution_count": 9, |
|
"id": "41c1f1af-ae20-423b-bf7c-efd7f8c2751b", |
|
"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": 10, |
|
"id": "eb537563-e393-47ca-9af2-a8ea7393edd9", |
|
"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 or social media 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": 36, |
|
"id": "033568d2-3f1a-43ac-a288-7a65b4ea86a5", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_links(url):\n", |
|
" website = Website(url)\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model=GPT_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": 12, |
|
"id": "d8f316ac-f0b1-42d9-88a8-0a61fcb0023d", |
|
"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", |
|
" print(f\"Processing {link['url']}...\")\n", |
|
" result += f\"\\n\\n{link['type']}\\n\"\n", |
|
" result += Website(link[\"url\"]).get_contents()\n", |
|
" return result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "016e065a-ac5a-48c0-bc4b-e916e9801384", |
|
"metadata": {}, |
|
"source": [ |
|
"#### System Message" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 18, |
|
"id": "ed1c6068-5f4f-47a7-ab97-738dfb94e057", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"system_message = \"You are an assistant that analyzes the contents of a company website landing page \\\n", |
|
"and creates a short brochure about the company for prospective customers, investors and recruits. \\\n", |
|
"You are also provided with the tone, and the target audience. Provide an appropriate answer. Respond in markdown.\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "6d4f594c-927d-440f-8aae-33cfeb9c445c", |
|
"metadata": {}, |
|
"source": [ |
|
"#### LLM Call Functions" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 40, |
|
"id": "5b6a0379-3465-4c04-a553-4e4cdb9064b9", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def stream_gpt(prompt,company_name,url):\n", |
|
" messages = [\n", |
|
" {\"role\": \"user\", \"content\": prompt},\n", |
|
" {\"role\":\"system\",\"content\":system_message}\n", |
|
" ]\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=GPT_MODEL,\n", |
|
" messages=messages,\n", |
|
" stream=True\n", |
|
" )\n", |
|
" result = \"\"\n", |
|
" for chunk in stream:\n", |
|
" result += chunk.choices[0].delta.content or \"\"\n", |
|
" yield result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 21, |
|
"id": "a2194e1d-4e99-4127-9515-aa9353382bc6", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def stream_claude(prompt):\n", |
|
" result = claude.messages.stream(\n", |
|
" model=CLAUDE_MODEL,\n", |
|
" max_tokens=1000,\n", |
|
" temperature=0.7,\n", |
|
" system=system_message,\n", |
|
" messages=[\n", |
|
" {\"role\": \"user\", \"content\": prompt},\n", |
|
" ],\n", |
|
" )\n", |
|
" response = \"\"\n", |
|
" with result as stream:\n", |
|
" for text in stream.text_stream:\n", |
|
" response += text or \"\"\n", |
|
" yield response" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "64adf26c-33b2-4589-8df6-dc5d6da71420", |
|
"metadata": {}, |
|
"source": [ |
|
"#### Brochure Creation" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 13, |
|
"id": "8192f39f-508b-4592-a075-767db68672b3", |
|
"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": 32, |
|
"id": "8aebfabe-4d51-4ee7-a9d2-5a379e9427cb", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def create_brochure(company_name, url,model,tone,target):\n", |
|
" print('create brochure function called')\n", |
|
" prompt = f\"Please generate a company brochure for {company_name}.\"\n", |
|
" prompt += f\"Use a {tone} tone; and target content at {target}\"\n", |
|
" prompt += get_brochure_user_prompt(company_name,url)\n", |
|
" \n", |
|
" if model == \"GPT\":\n", |
|
" result = stream_gpt(prompt,company_name,url)\n", |
|
" elif model==\"Claude\":\n", |
|
" result = stream_claude(prompt,company_name,url)\n", |
|
" else:\n", |
|
" raise ValueError(\"Unknown model\")\n", |
|
" yield from result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "c5f4f97b-c9d0-4d4c-8b02-e6209ba2549c", |
|
"metadata": {}, |
|
"source": [ |
|
"#### Putting it all together : Gradio UI" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 22, |
|
"id": "33162303-9b49-46fe-a8e0-0d01be45685b", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"force_dark_mode = \"\"\"\n", |
|
"function refresh() {\n", |
|
" const url = new URL(window.location);\n", |
|
" if (url.searchParams.get('__theme') !== 'dark') {\n", |
|
" url.searchParams.set('__theme', 'dark');\n", |
|
" window.location.href = url.href;\n", |
|
" }\n", |
|
"}\n", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 41, |
|
"id": "47ab9a41-cecd-4c21-bd68-4a15966b80c4", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"* Running on local URL: http://127.0.0.1:7877\n", |
|
"\n", |
|
"To create a public link, set `share=True` in `launch()`.\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/html": [ |
|
"<div><iframe src=\"http://127.0.0.1:7877/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.HTML object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
}, |
|
{ |
|
"data": { |
|
"text/plain": [] |
|
}, |
|
"execution_count": 41, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
}, |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.vellum.ai/'}, {'type': 'careers page', 'url': 'https://www.vellum.ai/careers'}]}\n", |
|
"Processing https://www.vellum.ai/...\n", |
|
"Processing https://www.vellum.ai/careers...\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"gr.Interface(\n", |
|
" fn=create_brochure,\n", |
|
" inputs=[\n", |
|
" gr.Textbox(label='Company Name:'),\n", |
|
" gr.Textbox(label=\"Landing page URL including http:// or https://\"),\n", |
|
" gr.Dropdown(['GPT','Claude'],label='Select Model:'),\n", |
|
" gr.Dropdown(['Formal','Casual','Persuasive','Informative','Conversational'],label='Select Tone:'),\n", |
|
" gr.Dropdown(['Businesses','General Public','Students','Investors','Customers'],label='Select Target Audience:'),\n", |
|
" ],\n", |
|
" outputs = [gr.Markdown(label='Brochure')],\n", |
|
" flagging_mode = 'never',\n", |
|
" js = force_dark_mode\n", |
|
").launch(inbrowser=True)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "2b923b09-6738-450a-9035-2c8d1bb9cae6", |
|
"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": "3.11.11" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|