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.
 
 

494 lines
15 KiB

{
"cells": [
{
"cell_type": "markdown",
"id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5",
"metadata": {},
"source": [
"# End of week 1 exercise\n",
"\n",
"To demonstrate your familiarity with OpenAI API, and also Ollama, build a tool that takes a technical question, \n",
"and responds with an explanation. This is a tool that you will be able to use yourself during the course!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c1070317-3ed9-4659-abe3-828943230e03",
"metadata": {},
"outputs": [],
"source": [
"# imports\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\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f",
"metadata": {},
"outputs": [],
"source": [
"# constants\n",
"\n",
"MODEL_GPT = 'gpt-4o-mini'\n",
"MODEL_LLAMA = 'llama3.2'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1",
"metadata": {},
"outputs": [],
"source": [
"# set up environment\n",
"# Initialize and constants\n",
"\n",
"load_dotenv()\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": "38f13b72-eb43-4dbb-b80f-34f1625b6db8",
"metadata": {},
"outputs": [],
"source": [
"# A class to represent a Webpage\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)\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": "1d853b19-28d7-49fe-a2af-b53b080b37bf",
"metadata": {},
"outputs": [],
"source": [
"ed=Website(\"https://www.edwarddonner.com\")\n",
"ed.links"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a64ccffe-06c5-49d9-ae06-067b6052f1ec",
"metadata": {},
"outputs": [],
"source": [
"#multi shots prmopting \n",
"#shot 1) you should respond in JSON... \n",
"#shot 2) you should also respond in multi colored text\n",
"\n",
"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 yellow text.\"\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": "38c058d0-d326-40dd-9925-1644288865b1",
"metadata": {},
"outputs": [],
"source": [
"print(link_system_prompt)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ea606951-a65a-4075-a473-58e4cddaf096",
"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 += \"print output in yellow text\\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": "96893ce7-865e-47e5-b637-2fab13305d5c",
"metadata": {},
"outputs": [],
"source": [
"print(get_links_user_prompt(ed))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "716b214d-497e-49fb-a0de-5bf4edb0f6bd",
"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": "code",
"execution_count": null,
"id": "553b3d1c-4956-42d9-bd86-abaf764e3b5e",
"metadata": {},
"outputs": [],
"source": [
"anthropic = Website(\"https://edwarddonner.com\")\n",
"anthropic.links"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d7b198d-a39f-4553-9432-0aaa8abbb0ec",
"metadata": {},
"outputs": [],
"source": [
"get_links(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9d160a9e-a129-4d4f-be34-4ccc4e570c03",
"metadata": {},
"outputs": [],
"source": [
"#make a brouchore now\n",
"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": "6ce3de06-f228-4f8c-ad65-522b25c1dcf5",
"metadata": {},
"outputs": [],
"source": [
"print(get_all_details(\"https://edwarddonner.com\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7c019742-9586-4061-96ff-912af9802bb5",
"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",
"Output should be displayed in mindmap diagram format.\\\n",
"Also output should be in Hindi lanaguage.\"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8152a14f-91e8-4abc-89c7-6062934611fa",
"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": "009ab063-eb0e-4d6e-b833-406277a0c70f",
"metadata": {},
"outputs": [],
"source": [
"get_brochure_user_prompt(\"Edward Donner\", \"https://edwarddonner.com\") "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bcccadb8-11d6-4ddd-a24f-6ac1c2101419",
"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": "3606b154-8d28-49ca-8028-c064f196fe20",
"metadata": {},
"outputs": [],
"source": [
"create_brochure(\"Anthropic\", \"https://anthropic.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "757b9f43-9c23-477b-9928-d6bbbf0394bb",
"metadata": {},
"outputs": [],
"source": [
"#stream brochure\n",
"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)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ea4408f4-dbdc-4168-a843-034b9620fb38",
"metadata": {},
"outputs": [],
"source": [
"stream_brochure(\"HuggingFace\", \"https://huggingface.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "256765bb-a307-4fe0-9582-f03403a25e8d",
"metadata": {},
"outputs": [],
"source": [
"#define new system prompt for the question below\n",
"\n",
"system_prompt = \"Output should be in both English and Hindi lanaguage.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798",
"metadata": {},
"outputs": [],
"source": [
"# here is the question; type over this to ask something new , i.e. user_prompt\n",
"\n",
"user_prompt = question = \"\"\"\n",
"Please explain what this code does and why:\n",
"yield from {book.get(\"author\") for book in books if book.get(\"author\")}\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "60ce7000-a4a5-4cce-a261-e75ef45063b4",
"metadata": {},
"outputs": [],
"source": [
"# Get gpt-4o-mini to answer, with streaming\n",
"#stream result\n",
"def stream_code_explanation():\n",
" stream = openai.chat.completions.create(\n",
" model=MODEL,\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt}\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": "a7c79f95-6a4f-48b1-afed-42848e5d5975",
"metadata": {},
"outputs": [],
"source": [
"stream_code_explanation()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "350eb627-23a3-4215-82be-e5b8f99280e2",
"metadata": {},
"outputs": [],
"source": [
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
"HEADERS = {\"Content-Type\": \"application/json\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "652739e1-6edd-4b9d-8a44-8ea8191f45a4",
"metadata": {},
"outputs": [],
"source": [
"# Create a messages list using the same format that we used for OpenAI\n",
"messages = [\n",
" {\"role\": \"user\", \"content\": \"Please explain what this code does and why: yield from {book.get(\\\"author\\\") for book in books if book.get(\\\"author\\\")}\"}\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d1b895b-1ba2-4ea2-95a5-fe7a798a4157",
"metadata": {},
"outputs": [],
"source": [
"payload = {\n",
" \"model\": MODEL_LLAMA,\n",
" \"messages\": messages,\n",
" \"stream\": False\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538",
"metadata": {},
"outputs": [],
"source": [
"# Get Llama 3.2 to answer\n",
"response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n",
"print(response.json()['message']['content'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fd9b22dd-cc77-4f1d-80ca-da45fe122dab",
"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
}