Browse Source

adding day 2 exercise

pull/239/head
Vaibhav Khode 2 months ago
parent
commit
3f2b62f243
  1. 272
      week1/Intermediate Python.ipynb
  2. 484
      week1/community-contributions/day2 EXERCISE-VK.ipynb
  3. 351
      week1/day1.ipynb
  4. 202
      week1/day2 EXERCISE.ipynb

272
week1/Intermediate Python.ipynb

File diff suppressed because one or more lines are too long

484
week1/community-contributions/day2 EXERCISE-VK.ipynb

@ -0,0 +1,484 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "d15d8294-3328-4e07-ad16-8a03e9bbfdb9",
"metadata": {},
"source": [
"# Welcome to your first assignment!\n",
"\n",
"Instructions are below. Please give this a try, and look in the solutions folder if you get stuck (or feel free to ask me!)"
]
},
{
"cell_type": "markdown",
"id": "ada885d9-4d42-4d9b-97f0-74fbbbfe93a9",
"metadata": {},
"source": [
"<table style=\"margin: 0; text-align: left;\">\n",
" <tr>\n",
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
" <img src=\"../resources.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
" </td>\n",
" <td>\n",
" <h2 style=\"color:#f71;\">Just before we get to the assignment --</h2>\n",
" <span style=\"color:#f71;\">I thought I'd take a second to point you at this page of useful resources for the course. This includes links to all the slides.<br/>\n",
" <a href=\"https://edwarddonner.com/2024/11/13/llm-engineering-resources/\">https://edwarddonner.com/2024/11/13/llm-engineering-resources/</a><br/>\n",
" Please keep this bookmarked, and I'll continue to add more useful links there over time.\n",
" </span>\n",
" </td>\n",
" </tr>\n",
"</table>"
]
},
{
"cell_type": "markdown",
"id": "6e9fa1fc-eac5-4d1d-9be4-541b3f2b3458",
"metadata": {},
"source": [
"# HOMEWORK EXERCISE ASSIGNMENT\n",
"\n",
"Upgrade the day 1 project to summarize a webpage to use an Open Source model running locally via Ollama rather than OpenAI\n",
"\n",
"You'll be able to use this technique for all subsequent projects if you'd prefer not to use paid APIs.\n",
"\n",
"**Benefits:**\n",
"1. No API charges - open-source\n",
"2. Data doesn't leave your box\n",
"\n",
"**Disadvantages:**\n",
"1. Significantly less power than Frontier Model\n",
"\n",
"## Recap on installation of Ollama\n",
"\n",
"Simply visit [ollama.com](https://ollama.com) and install!\n",
"\n",
"Once complete, the ollama server should already be running locally. \n",
"If you visit: \n",
"[http://localhost:11434/](http://localhost:11434/)\n",
"\n",
"You should see the message `Ollama is running`. \n",
"\n",
"If not, bring up a new Terminal (Mac) or Powershell (Windows) and enter `ollama serve` \n",
"And in another Terminal (Mac) or Powershell (Windows), enter `ollama pull llama3.2` \n",
"Then try [http://localhost:11434/](http://localhost:11434/) again.\n",
"\n",
"If Ollama is slow on your machine, try using `llama3.2:1b` as an alternative. Run `ollama pull llama3.2:1b` from a Terminal or Powershell, and change the code below from `MODEL = \"llama3.2\"` to `MODEL = \"llama3.2:1b\"`"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "29ddd15d-a3c5-4f4e-a678-873f56162724",
"metadata": {},
"outputs": [],
"source": [
"# Constants\n",
"\n",
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
"HEADERS = {\"Content-Type\": \"application/json\"}\n",
"MODEL = \"llama3.2\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dac0a679-599c-441f-9bf2-ddc73d35b940",
"metadata": {},
"outputs": [],
"source": [
"# Create a messages list using the same format that we used for OpenAI\n",
"\n",
"messages = [\n",
" {\"role\": \"user\", \"content\": \"Describe some of the business applications of Generative AI\"}\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7bb9c624-14f0-4945-a719-8ddb64f66f47",
"metadata": {},
"outputs": [],
"source": [
"payload = {\n",
" \"model\": MODEL,\n",
" \"messages\": messages,\n",
" \"stream\": False\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "479ff514-e8bd-4985-a572-2ea28bb4fa40",
"metadata": {},
"outputs": [],
"source": [
"# Let's just make sure the model is loaded\n",
"\n",
"!ollama pull llama3.2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "42b9f644-522d-4e05-a691-56e7658c0ea9",
"metadata": {},
"outputs": [],
"source": [
"# If this doesn't work for any reason, try the 2 versions in the following cells\n",
"# And double check the instructions in the 'Recap on installation of Ollama' at the top of this lab\n",
"# And if none of that works - contact me!\n",
"\n",
"response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n",
"print(response.json()['message']['content'])\n",
"#print(response.json())"
]
},
{
"cell_type": "markdown",
"id": "6a021f13-d6a1-4b96-8e18-4eae49d876fe",
"metadata": {},
"source": [
"# Introducing the ollama package\n",
"\n",
"And now we'll do the same thing, but using the elegant ollama python package instead of a direct HTTP call.\n",
"\n",
"Under the hood, it's making the same call as above to the ollama server running at localhost:11434"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7745b9c4-57dc-4867-9180-61fa5db55eb8",
"metadata": {},
"outputs": [],
"source": [
"import ollama\n",
"\n",
"response = ollama.chat(model=MODEL, messages=messages)\n",
"print(response['message']['content'])"
]
},
{
"cell_type": "markdown",
"id": "a4704e10-f5fb-4c15-a935-f046c06fb13d",
"metadata": {},
"source": [
"## Alternative approach - using OpenAI python library to connect to Ollama"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "23057e00-b6fc-4678-93a9-6b31cb704bff",
"metadata": {},
"outputs": [],
"source": [
"# There's actually an alternative approach that some people might prefer\n",
"# You can use the OpenAI client python library to call Ollama:\n",
"\n",
"from openai import OpenAI\n",
"ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
"\n",
"response = ollama_via_openai.chat.completions.create(\n",
" model=MODEL,\n",
" messages=messages\n",
")\n",
"\n",
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "bc7d1de3-e2ac-46ff-a302-3b4ba38c4c90",
"metadata": {},
"source": [
"## Also trying the amazing reasoning model DeepSeek\n",
"\n",
"Here we use the version of DeepSeek-reasoner that's been distilled to 1.5B. \n",
"This is actually a 1.5B variant of Qwen that has been fine-tuned using synethic data generated by Deepseek R1.\n",
"\n",
"Other sizes of DeepSeek are [here](https://ollama.com/library/deepseek-r1) all the way up to the full 671B parameter version, which would use up 404GB of your drive and is far too large for most!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cf9eb44e-fe5b-47aa-b719-0bb63669ab3d",
"metadata": {},
"outputs": [],
"source": [
"!ollama pull deepseek-r1:1.5b"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1d3d554b-e00d-4c08-9300-45e073950a76",
"metadata": {},
"outputs": [],
"source": [
"# This may take a few minutes to run! You should then see a fascinating \"thinking\" trace inside <think> tags, followed by some decent definitions\n",
"\n",
"response = ollama_via_openai.chat.completions.create(\n",
" model=\"deepseek-r1:1.5b\",\n",
" messages=[{\"role\": \"user\", \"content\": \"Please give definitions of some core concepts behind LLMs: a neural network, attention and the transformer\"}]\n",
")\n",
"\n",
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "1622d9bb-5c68-4d4e-9ca4-b492c751f898",
"metadata": {},
"source": [
"# NOW the exercise for you\n",
"\n",
"Take the code from day1 and incorporate it here, to build a website summarizer that uses Llama 3.2 running locally instead of OpenAI; use either of the above approaches."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6de38216-6d1c-48c4-877b-86d403f4e0f8",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display\n",
"import ollama\n",
"\n",
"# If you get an error running this cell, then please head over to the troubleshooting notebook!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9910f239-0dc4-434d-ae26-ccbca0ee2b6f",
"metadata": {},
"outputs": [],
"source": [
"MODEL = \"llama3.2\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c46e6fdb-b445-47bf-909f-c513183f5aed",
"metadata": {},
"outputs": [],
"source": [
"# A class to represent a Webpage\n",
"# If you're not familiar with Classes, check out the \"Intermediate Python\" notebook\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",
" def __init__(self, url):\n",
" \"\"\"\n",
" Create this Website object from the given url using the BeautifulSoup library\n",
" \"\"\"\n",
" self.url = url\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
" self.title = soup.title.string if soup.title else \"No title found\"\n",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "644f4ebb-9657-4560-adea-f7b0da76bda7",
"metadata": {},
"outputs": [],
"source": [
"# Let's try one out. Change the website and add print statements to follow along.\n",
"\n",
"ed = Website(\"https://edwarddonner.com\")\n",
"print(ed.title)\n",
"print(ed.text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "324a0a20-e12d-46fc-90bc-8a0cd74a6d71",
"metadata": {},
"outputs": [],
"source": [
"# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n",
"\n",
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n",
"and provides a short summary, ignoring text that might be navigation related. \\\n",
"Respond in markdown.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "943a7c0b-a7bd-4970-a040-f24638772cc9",
"metadata": {},
"outputs": [],
"source": [
"# A function that writes a User Prompt that asks for summaries of websites:\n",
"\n",
"def user_prompt_for(website):\n",
" user_prompt = f\"You are looking at a website titled {website.title}\"\n",
" user_prompt += \"The contents of this website is as follows; \\\n",
"please provide a short summary of this website in markdown. \\\n",
"If it includes news or announcements, then summarize these too.\\n\\n\"\n",
" user_prompt += website.text\n",
" return user_prompt"
]
},
{
"cell_type": "markdown",
"id": "0fc3379b-2130-4f24-9aef-ad36b2c5a09c",
"metadata": {},
"source": [
"## Messages\n",
"\n",
"The API from Ollama expects the same message format as OpenAI:\n",
"\n",
"```\n",
"[\n",
" {\"role\": \"system\", \"content\": \"system message goes here\"},\n",
" {\"role\": \"user\", \"content\": \"user message goes here\"}\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "00d5da9e-b629-4617-9b8a-0573a3249eed",
"metadata": {},
"outputs": [],
"source": [
"# See how this function creates exactly the format above\n",
"\n",
"def messages_for(website):\n",
" return [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "80171f18-80f6-4241-b13c-02038cc7a42c",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the OpenAI API. You will get very familiar with this!\n",
"\n",
"def summarize(url):\n",
" website = Website(url)\n",
" messages = messages_for(website) \n",
" response = ollama.chat(model=MODEL, messages=messages)\n",
" return response['message']['content']\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "731a3c63-50d1-4bd9-9744-2cef6ed20745",
"metadata": {},
"outputs": [],
"source": [
"summarize(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b527afbc-e764-4e53-adb6-78be2b611786",
"metadata": {},
"outputs": [],
"source": [
"# A function to display this nicely in the Jupyter output, using markdown\n",
"\n",
"def display_summary(url):\n",
" summary = summarize(url)\n",
" display(Markdown(summary))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6dedb19a-25a1-42e2-a92f-46d6c7d71faf",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "433735b3-dbe8-4774-ab2b-3f866c2b6607",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://cnn.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8944cd3d-f4b9-4274-be66-0d017b4d5272",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://anthropic.com\")"
]
}
],
"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
}

351
week1/day1.ipynb

@ -90,7 +90,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
"metadata": {},
"outputs": [],
@ -129,10 +129,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"id": "7b87cadb-d513-4303-baee-a37b6f938e4d",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"API key found and looks good so far!\n"
]
}
],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
@ -153,7 +161,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"id": "019974d9-f3ad-4a8a-b5f9-0a3719aea2d3",
"metadata": {},
"outputs": [],
@ -174,10 +182,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"id": "a58394bf-1e45-46af-9bfd-01e24da6f49a",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Hello! It’s great to hear from you! How can I assist you today?\n"
]
}
],
"source": [
"# To give you a preview -- calling OpenAI with these messages is this easy. Any problems, head over to the Troubleshooting notebook.\n",
"\n",
@ -196,7 +212,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 8,
"id": "c5e793b2-6775-426a-a139-4848291d0463",
"metadata": {},
"outputs": [],
@ -226,10 +242,65 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"id": "2ef960cf-6dc2-4cda-afb3-b38be12f4c97",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Home - Edward Donner\n",
"Home\n",
"Connect Four\n",
"Outsmart\n",
"An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n",
"About\n",
"Posts\n",
"Well, hi there.\n",
"I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n",
"very\n",
"amateur) and losing myself in\n",
"Hacker News\n",
", nodding my head sagely to things I only half understand.\n",
"I’m the co-founder and CTO of\n",
"Nebula.io\n",
". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n",
"acquired in 2021\n",
".\n",
"We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n",
"patented\n",
"our matching model, and our award-winning platform has happy customers and tons of press coverage.\n",
"Connect\n",
"with me for more!\n",
"January 23, 2025\n",
"LLM Workshop – Hands-on with Agents – resources\n",
"December 21, 2024\n",
"Welcome, SuperDataScientists!\n",
"November 13, 2024\n",
"Mastering AI and LLM Engineering – Resources\n",
"October 16, 2024\n",
"From Software Engineer to AI Data Scientist – resources\n",
"Navigation\n",
"Home\n",
"Connect Four\n",
"Outsmart\n",
"An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n",
"About\n",
"Posts\n",
"Get in touch\n",
"ed [at] edwarddonner [dot] com\n",
"www.edwarddonner.com\n",
"Follow me\n",
"LinkedIn\n",
"Twitter\n",
"Facebook\n",
"Subscribe to newsletter\n",
"Type your email…\n",
"Subscribe\n"
]
}
],
"source": [
"# Let's try one out. Change the website and add print statements to follow along.\n",
"\n",
@ -258,7 +329,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"id": "abdb8417-c5dc-44bc-9bee-2e059d162699",
"metadata": {},
"outputs": [],
@ -272,7 +343,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"id": "f0275b1b-7cfe-4f9d-abfa-7650d378da0c",
"metadata": {},
"outputs": [],
@ -290,10 +361,67 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"id": "26448ec4-5c00-4204-baec-7df91d11ff2e",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"You are looking at a website titled Home - Edward Donner\n",
"The contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\n",
"\n",
"Home\n",
"Connect Four\n",
"Outsmart\n",
"An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n",
"About\n",
"Posts\n",
"Well, hi there.\n",
"I’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\n",
"very\n",
"amateur) and losing myself in\n",
"Hacker News\n",
", nodding my head sagely to things I only half understand.\n",
"I’m the co-founder and CTO of\n",
"Nebula.io\n",
". We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\n",
"acquired in 2021\n",
".\n",
"We work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\n",
"patented\n",
"our matching model, and our award-winning platform has happy customers and tons of press coverage.\n",
"Connect\n",
"with me for more!\n",
"January 23, 2025\n",
"LLM Workshop – Hands-on with Agents – resources\n",
"December 21, 2024\n",
"Welcome, SuperDataScientists!\n",
"November 13, 2024\n",
"Mastering AI and LLM Engineering – Resources\n",
"October 16, 2024\n",
"From Software Engineer to AI Data Scientist – resources\n",
"Navigation\n",
"Home\n",
"Connect Four\n",
"Outsmart\n",
"An arena that pits LLMs against each other in a battle of diplomacy and deviousness\n",
"About\n",
"Posts\n",
"Get in touch\n",
"ed [at] edwarddonner [dot] com\n",
"www.edwarddonner.com\n",
"Follow me\n",
"LinkedIn\n",
"Twitter\n",
"Facebook\n",
"Subscribe to newsletter\n",
"Type your email…\n",
"Subscribe\n"
]
}
],
"source": [
"print(user_prompt_for(ed))"
]
@ -319,7 +447,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"id": "f25dcd35-0cd0-4235-9f64-ac37ed9eaaa5",
"metadata": {},
"outputs": [],
@ -332,10 +460,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 14,
"id": "21ed95c5-7001-47de-a36d-1d6673b403ce",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Oh, we're starting with the big questions, huh? Well, brace yourself: 2 + 2 equals 4. Shocking, I know!\n"
]
}
],
"source": [
"# To give you a preview -- calling OpenAI with system and user messages:\n",
"\n",
@ -353,7 +489,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 15,
"id": "0134dfa4-8299-48b5-b444-f2a8c3403c88",
"metadata": {},
"outputs": [],
@ -369,10 +505,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 16,
"id": "36478464-39ee-485c-9f3f-6a4e458dbc9c",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[{'role': 'system',\n",
" 'content': 'You are an assistant that analyzes the contents of a website and provides a short summary, ignoring text that might be navigation related. Respond in markdown.'},\n",
" {'role': 'user',\n",
" 'content': 'You are looking at a website titled Home - Edward Donner\\nThe contents of this website is as follows; please provide a short summary of this website in markdown. If it includes news or announcements, then summarize these too.\\n\\nHome\\nConnect Four\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nWell, hi there.\\nI’m Ed. I like writing code and experimenting with LLMs, and hopefully you’re here because you do too. I also enjoy DJing (but I’m badly out of practice), amateur electronic music production (\\nvery\\namateur) and losing myself in\\nHacker News\\n, nodding my head sagely to things I only half understand.\\nI’m the co-founder and CTO of\\nNebula.io\\n. We’re applying AI to a field where it can make a massive, positive impact: helping people discover their potential and pursue their reason for being. Recruiters use our product today to source, understand, engage and manage talent. I’m previously the founder and CEO of AI startup untapt,\\nacquired in 2021\\n.\\nWe work with groundbreaking, proprietary LLMs verticalized for talent, we’ve\\npatented\\nour matching model, and our award-winning platform has happy customers and tons of press coverage.\\nConnect\\nwith me for more!\\nJanuary 23, 2025\\nLLM Workshop – Hands-on with Agents – resources\\nDecember 21, 2024\\nWelcome, SuperDataScientists!\\nNovember 13, 2024\\nMastering AI and LLM Engineering – Resources\\nOctober 16, 2024\\nFrom Software Engineer to AI Data Scientist – resources\\nNavigation\\nHome\\nConnect Four\\nOutsmart\\nAn arena that pits LLMs against each other in a battle of diplomacy and deviousness\\nAbout\\nPosts\\nGet in touch\\ned [at] edwarddonner [dot] com\\nwww.edwarddonner.com\\nFollow me\\nLinkedIn\\nTwitter\\nFacebook\\nSubscribe to newsletter\\nType your email…\\nSubscribe'}]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Try this out, and then try for a few more websites\n",
"\n",
@ -389,7 +539,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 17,
"id": "905b9919-aba7-45b5-ae65-81b3d1d78e34",
"metadata": {},
"outputs": [],
@ -407,17 +557,28 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 18,
"id": "05e38d41-dfa4-4b20-9c96-c46ea75d9fb5",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"\"# Summary of Edward Donner's Website\\n\\nEdward Donner's website showcases his interests and expertise in coding and artificial intelligence, particularly in the realm of large language models (LLMs). He is the co-founder and CTO of Nebula.io, a company focused on enhancing talent discovery through AI. The site highlights his background as the former founder and CEO of the AI startup untapt, which was acquired in 2021.\\n\\n## Notable Features:\\n- **Personal Introduction**: Ed shares his passion for coding, LLM experimentation, and electronic music.\\n- **Company Overview**: Nebula.io leverages advanced LLMs for talent management and has received positive attention for its innovative model.\\n \\n## Recent Announcements:\\n- **January 23, 2025**: LLM Workshop – Hands-on with Agents – Resources\\n- **December 21, 2024**: Welcome, SuperDataScientists!\\n- **November 13, 2024**: Mastering AI and LLM Engineering – Resources\\n- **October 16, 2024**: From Software Engineer to AI Data Scientist – Resources\\n\\nEd invites connections and engagement through various platforms, emphasizing his commitment to sharing knowledge and resources in the AI field.\""
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"summarize(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 19,
"id": "3d926d59-450e-4609-92ba-2d6f244f1342",
"metadata": {},
"outputs": [],
@ -431,10 +592,38 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 20,
"id": "3018853a-445f-41ff-9560-d925d1774b2f",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/markdown": [
"# Summary of Edward Donner's Website\n",
"\n",
"Edward Donner's website showcases his interests and professional background in coding and AI, particularly in the realm of Large Language Models (LLMs). He is the co-founder and CTO of Nebula.io, a company focused on leveraging AI for talent discovery and engagement, with a successful history that includes founding the now-acquired AI startup untapt.\n",
"\n",
"## Notable Features:\n",
"- **Connect Four**: A project designed to engage LLMs in competitive scenarios focused on diplomacy and strategy.\n",
"- **Outsmart**: Another initiative that revolves around LLM interactions.\n",
"- **Personal Interests**: Ed enjoys DJing, electronic music production, and engaging with technology news on Hacker News.\n",
"\n",
"## News and Announcements:\n",
"- **January 23, 2025**: Publication of resources from the \"LLM Workshop – Hands-on with Agents.\"\n",
"- **December 21, 2024**: A welcoming message to \"SuperDataScientists.\"\n",
"- **November 13, 2024**: Release of resources for \"Mastering AI and LLM Engineering.\"\n",
"- **October 16, 2024**: Sharing resources for transitioning from Software Engineer to AI Data Scientist.\n",
"\n",
"Users can connect with Ed through various social media platforms and subscribe to his newsletter for updates."
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display_summary(\"https://edwarddonner.com\")"
]
@ -457,20 +646,70 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 21,
"id": "45d83403-a24c-44b5-84ac-961449b4008f",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/markdown": [
"# Summary of CNN Website Content\n",
"\n",
"CNN provides breaking news, articles, and videos on various topics including politics, business, entertainment, health, science, and more. The website covers current events from both the U.S. and international perspectives, with specific sections dedicated to ongoing crises such as the Ukraine-Russia War and the Israel-Hamas conflict.\n",
"\n",
"### Recent News Highlights:\n",
"- **Politics**: Coverage of significant interactions involving U.S. and international leaders, particularly focusing on the recent meeting between Trump's administration and Ukrainian President Zelensky. \n",
"- **International Affairs**: Speculations regarding the solidarity shown by European leaders towards Ukraine amidst political exchanges.\n",
"- **Health & Environment**: WHO's report on potential water contamination in Congo and discussions surrounding mental health and substance use.\n",
"- **Business**: A Microsoft outage affecting thousands of users, and analysis of the impact of Trump's potential tariffs.\n",
"- **Entertainment**: Reports on the passing of R&B singer Angie Stone and the social dynamics surrounding recent awards shows.\n",
"\n",
"The site also features a section for user feedback, aiming to enhance viewer experience, and multiple multimedia options for consuming content such as live news, podcasts, and video segments."
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display_summary(\"https://cnn.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 22,
"id": "75e9fd40-b354-4341-991e-863ef2e59db7",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/markdown": [
"# Anthropic Website Summary\n",
"\n",
"Anthropic is a San Francisco-based AI safety and research company focused on creating reliable and beneficial AI systems. The company emphasizes AI safety and employs an interdisciplinary team with expertise in machine learning, physics, policy, and product development.\n",
"\n",
"## Key Offerings\n",
"- **Claude 3.7 Sonnet**: Their most advanced AI model, noted for its hybrid reasoning capabilities.\n",
"- **Claude Code**: A new tool designed for coding tasks.\n",
"\n",
"## Recent Announcements\n",
"- **September 4, 2024**: Launch of Claude 3.7 Sonnet, highlighting its intelligence and hybrid reasoning features.\n",
"- **March 8, 2023**: Release of a document outlining core views on AI safety, detailing when, why, what, and how AI should be managed.\n",
"- **December 15, 2022**: Introduction of a research paper on 'Constitutional AI,' focusing on ensuring harmlessness through AI feedback.\n",
"\n",
"Anthropic invites collaboration and has open roles for those interested in joining their mission of advancing AI safety and research."
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display_summary(\"https://anthropic.com\")"
]
@ -509,30 +748,68 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 25,
"id": "00743dac-0e70-45b7-879a-d7293a6f68a6",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1. Senior technology leader with extensive experience in driving digital transformation and automation for Standard Chartered Bank's global engineering team, focusing on over 50 technology assets.\n",
"2. Expert in technology strategy and transformation, successfully implementing advanced cybersecurity measures and embedding data quality throughout the software development lifecycle.\n",
"3. Proven track record in delivering AI-driven solutions that enhance decision-making and customer experience while cultivating high-performance teams through mentorship.\n",
"4. Achievements include the successful delivery of a cloud-based SAP SuccessFactors HRMS and Recruitment solution, as well as a digital employee communication platform.\n",
"5. Recognized for excellence with the \"Going Extra Mile (GEM)\" award in 2022, emphasizing commitment to quality and stakeholder collaboration.\n"
]
}
],
"source": [
"# Step 1: Create your prompts\n",
"\n",
"system_prompt = \"something here\"\n",
"system_prompt = \"you are a career coach and resume expert. \"\n",
"user_prompt = \"\"\"\n",
" Lots of text\n",
" Can be pasted here\n",
" I am pasting my resume content below. You have to summarise my resume not more than 5 statements. \n",
" \n",
" Director – Technology (Strategy & Talent)\n",
"Standard Chartered Bank, Singapore | Nov 2021 – Present\n",
"Role: Led the global team of 30+ engineers, overseeing Digital Transformation, Quality Engineering, Automation, Data Quality and Compliance for 50+ Technology Assets. Focused on Cloud, On-Prem, Mobile and Data solutions across HR, Corporate Affairs, Brand & Marketing, Property and Supply Chain Management domains. \n",
"\n",
"Key Responsibilities: \n",
"•\tLed the global engineering team, driving Digital Transformation and Automation to deliver high quality software solutions.\n",
"•\tSpearheaded Technology Strategy and Transformation for Engineering Excellence. \n",
"•\tChampioned DevOps and Automation adoption to accelerate and streamline delivery. \n",
"•\tImplemented advanced Cybersecurity measures to reduce risks and deliver secure, stable and reliable solutions. \n",
"•\tDelivered AI-driven solutions, enhancing decision making, improving efficiency and enhancing customer experience. \n",
"•\tBuilt robust Automation and Performance engineering capabilities within the team. \n",
"•\tEmbedded Data Quality and Data Assurance throughout solution design, engineering and delivery lifecycle. \n",
"•\tReviewed Architecture, Design, Requirements and Quality aligned to SDLC Standards.\n",
"•\tPartnered with Auditors to ensure compliance with Technology Standards. \n",
"•\tCultivated and mentored a high-performance engineering team.\n",
"•\tSeamlessly collaborated with Stakeholders and managed vendors best outcome.\n",
"\n",
"Key Achievements: \n",
"•\tDelivered Cloud based SAP SuccessFactors HRMS and Recruitment solution.\n",
"•\tImplemented Automated Regression for HRMS GCP Datacenter migration.\n",
"•\tRedesigned HRMS to IAM interface, addressing Security Audit action. \n",
"•\tDelivered cloud based Digital Employee Communication platform. \n",
"•\tReceived “Going Extra Mile (GEM)” award for year 2022. \n",
"\n",
"\n",
"\"\"\"\n",
"\n",
"# Step 2: Make the messages list\n",
"\n",
"messages = [] # fill this in\n",
"messages = [{\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt}] # fill this in\n",
"\n",
"# Step 3: Call OpenAI\n",
"\n",
"response =\n",
"response = openai.chat.completions.create(model = \"gpt-4o-mini\",messages = messages)\n",
"\n",
"# Step 4: print the result\n",
"\n",
"print("
"print(response.choices[0].message.content)\n"
]
},
{

202
week1/day2 EXERCISE.ipynb

@ -146,7 +146,8 @@
"# And if none of that works - contact me!\n",
"\n",
"response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n",
"print(response.json()['message']['content'])"
"print(response.json()['message']['content'])\n",
"#print(response.json())"
]
},
{
@ -259,7 +260,204 @@
"id": "6de38216-6d1c-48c4-877b-86d403f4e0f8",
"metadata": {},
"outputs": [],
"source": []
"source": [
"# imports\n",
"\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display\n",
"import ollama\n",
"\n",
"# If you get an error running this cell, then please head over to the troubleshooting notebook!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9910f239-0dc4-434d-ae26-ccbca0ee2b6f",
"metadata": {},
"outputs": [],
"source": [
"MODEL = \"llama3.2\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c46e6fdb-b445-47bf-909f-c513183f5aed",
"metadata": {},
"outputs": [],
"source": [
"# A class to represent a Webpage\n",
"# If you're not familiar with Classes, check out the \"Intermediate Python\" notebook\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",
" def __init__(self, url):\n",
" \"\"\"\n",
" Create this Website object from the given url using the BeautifulSoup library\n",
" \"\"\"\n",
" self.url = url\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
" self.title = soup.title.string if soup.title else \"No title found\"\n",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "644f4ebb-9657-4560-adea-f7b0da76bda7",
"metadata": {},
"outputs": [],
"source": [
"# Let's try one out. Change the website and add print statements to follow along.\n",
"\n",
"ed = Website(\"https://edwarddonner.com\")\n",
"print(ed.title)\n",
"print(ed.text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "324a0a20-e12d-46fc-90bc-8a0cd74a6d71",
"metadata": {},
"outputs": [],
"source": [
"# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n",
"\n",
"system_prompt = \"You are an assistant that analyzes the contents of a website \\\n",
"and provides a short summary, ignoring text that might be navigation related. \\\n",
"Respond in markdown.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "943a7c0b-a7bd-4970-a040-f24638772cc9",
"metadata": {},
"outputs": [],
"source": [
"# A function that writes a User Prompt that asks for summaries of websites:\n",
"\n",
"def user_prompt_for(website):\n",
" user_prompt = f\"You are looking at a website titled {website.title}\"\n",
" user_prompt += \"The contents of this website is as follows; \\\n",
"please provide a short summary of this website in markdown. \\\n",
"If it includes news or announcements, then summarize these too.\\n\\n\"\n",
" user_prompt += website.text\n",
" return user_prompt"
]
},
{
"cell_type": "markdown",
"id": "0fc3379b-2130-4f24-9aef-ad36b2c5a09c",
"metadata": {},
"source": [
"## Messages\n",
"\n",
"The API from Ollama expects the same message format as OpenAI:\n",
"\n",
"```\n",
"[\n",
" {\"role\": \"system\", \"content\": \"system message goes here\"},\n",
" {\"role\": \"user\", \"content\": \"user message goes here\"}\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "00d5da9e-b629-4617-9b8a-0573a3249eed",
"metadata": {},
"outputs": [],
"source": [
"# See how this function creates exactly the format above\n",
"\n",
"def messages_for(website):\n",
" return [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
" ]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "80171f18-80f6-4241-b13c-02038cc7a42c",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the OpenAI API. You will get very familiar with this!\n",
"\n",
"def summarize(url):\n",
" website = Website(url)\n",
" messages = messages_for(website) \n",
" response = ollama.chat(model=MODEL, messages=messages)\n",
" return response['message']['content']\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "731a3c63-50d1-4bd9-9744-2cef6ed20745",
"metadata": {},
"outputs": [],
"source": [
"summarize(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b527afbc-e764-4e53-adb6-78be2b611786",
"metadata": {},
"outputs": [],
"source": [
"# A function to display this nicely in the Jupyter output, using markdown\n",
"\n",
"def display_summary(url):\n",
" summary = summarize(url)\n",
" display(Markdown(summary))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6dedb19a-25a1-42e2-a92f-46d6c7d71faf",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://edwarddonner.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "433735b3-dbe8-4774-ab2b-3f866c2b6607",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://cnn.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8944cd3d-f4b9-4274-be66-0d017b4d5272",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://anthropic.com\")"
]
}
],
"metadata": {

Loading…
Cancel
Save