brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #491 from Zhufeng-Qiu/zephyr-week1-week2

Browse Source 
Added my contributions to community-contributions of week1/week2
This commit is contained in:
Ed Donner
2025-07-06 10:06:56 -04:00
committed by GitHub
parent f210c53b96 a3b03fcd8f
commit 6894e5a2cd
5 changed files with 1688 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

271
week1/community-contributions/day1-dotabuff-summarization.ipynb Normal file
View File

@@ -0,0 +1,271 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "032a76d2-a112-4c49-bd32-fe6c87f6ec19",
"metadata": {},
"source": [
"## Dota Game Assistant\n",
"\n",
"This script retrieves and summarizes information about a specified hero from `dotabuff.com` website"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "04b24159-55d1-4eaf-bc19-474cec71cc3b",
"metadata": {},
"outputs": [],
"source": [
"!pip install selenium\n",
"!pip install webdriver-manager"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "14d26510-6613-4c1a-a346-159d906d111c",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import requests\n",
"from dotenv import load_dotenv\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display\n",
"from openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f9c8ea1e-8881-4f50-953d-ca7f462d8a32",
"metadata": {},
"outputs": [],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
"load_dotenv(override=True)\n",
"api_key = os.getenv('OPENAI_API_KEY')\n",
"\n",
"# Check the key\n",
"\n",
"if not api_key:\n",
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
"elif not api_key.startswith(\"sk-proj-\"):\n",
" print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
"elif api_key.strip() != api_key:\n",
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
"else:\n",
" print(\"API key found and looks good so far!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "02febcac-9a21-4322-b2ea-748972312165",
"metadata": {},
"outputs": [],
"source": [
"openai = OpenAI()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bb7dd822-962e-4b34-a743-c14809764e4a",
"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",
"from selenium import webdriver\n",
"from selenium.webdriver.chrome.service import Service\n",
"from selenium.webdriver.chrome.options import Options\n",
"from selenium.webdriver.common.by import By\n",
"from selenium.webdriver.support.ui import WebDriverWait\n",
"from selenium.webdriver.support import expected_conditions as EC\n",
"from webdriver_manager.chrome import ChromeDriverManager\n",
"from bs4 import BeautifulSoup\n",
"\n",
"class Website:\n",
" def __init__(self, url, wait_time=10):\n",
" \"\"\"\n",
" Create this Website object from the given URL using Selenium and BeautifulSoup.\n",
" Uses headless Chrome to load JavaScript content.\n",
" \"\"\"\n",
" self.url = url\n",
"\n",
" # Configure headless Chrome\n",
" options = Options()\n",
" options.headless = True\n",
" options.add_argument(\"--disable-gpu\")\n",
" options.add_argument(\"--no-sandbox\")\n",
"\n",
" # Start the driver\n",
" service = Service(ChromeDriverManager().install())\n",
" driver = webdriver.Chrome(service=service, options=options)\n",
"\n",
" try:\n",
" driver.get(url)\n",
"\n",
" # Wait until body is loaded (you can tweak the wait condition)\n",
" WebDriverWait(driver, wait_time).until(\n",
" EC.presence_of_element_located((By.TAG_NAME, \"body\"))\n",
" )\n",
"\n",
" html = driver.page_source\n",
" soup = BeautifulSoup(html, \"html.parser\")\n",
"\n",
" self.title = soup.title.string.strip() if soup.title else \"No title found\"\n",
"\n",
" # Remove unwanted tags\n",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
"\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
"\n",
" finally:\n",
" driver.quit()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9d833fbb-0115-4d99-a4e9-464f27900eab",
"metadata": {},
"outputs": [],
"source": [
"class DotaWebsite:\n",
" def __init__(self, hero):\n",
" web = Website(\"https://www.dotabuff.com/heroes\" + \"/\" + hero)\n",
" self.title = web.title\n",
" self.text = web.text"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a0a42c2b-c837-4d1b-b8f8-b2dbb8592a1a",
"metadata": {},
"outputs": [],
"source": [
"system_prompt = \"You are an game assistant that analyzes the contents of a website \\\n",
"and provides a short summary about facet selection, ability building, item building, best versus and worst versus, ignoring text that might be navigation related. \\\n",
"Respond in markdown.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7c05843d-6373-4a76-8cca-9c716a6ca13a",
"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 += \"\\nThe contents of this website is as follows; \\\n",
"please provide a short summary of provides a short summary about facet selection, ability building, item building, best versus and worst versus 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": "code",
"execution_count": null,
"id": "0145eee1-39e2-4f00-89ec-7acc6e375972",
"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": "76f389c0-572a-476b-9b4e-719c0ef10abb",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the OpenAI API. You will get very familiar with this!\n",
"\n",
"def summarize(hero):\n",
" website = DotaWebsite(hero)\n",
" response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages_for(website)\n",
" )\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fcb046b7-52a9-49ff-b7bc-d8f6c279df4c",
"metadata": {},
"outputs": [],
"source": [
"# A function to display this nicely in the Jupyter output, using markdown\n",
"\n",
"def display_summary(hero):\n",
" summary = summarize(hero)\n",
" display(Markdown(summary))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9befb685-2912-41a9-b2d9-ae33001494c0",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"axe\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bf1bb1d9-0351-44fc-8ebf-91aa47a81b42",
"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": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

459
week1/community-contributions/day2-EXERCISE-ollama-local.ipynb Normal file
View File

@@ -0,0 +1,459 @@
{
"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'])"
]
},
{
"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": "9f9e22da-b891-41f6-9ac9-bd0c0a5f4f44",
"metadata": {},
"source": [
"## Are you confused about why that works?\n",
"\n",
"It seems strange, right? We just used OpenAI code to call Ollama?? What's going on?!\n",
"\n",
"Here's the scoop:\n",
"\n",
"The python class `OpenAI` is simply code written by OpenAI engineers that makes calls over the internet to an endpoint. \n",
"\n",
"When you call `openai.chat.completions.create()`, this python code just makes a web request to the following url: \"https://api.openai.com/v1/chat/completions\"\n",
"\n",
"Code like this is known as a \"client library\" - it's just wrapper code that runs on your machine to make web requests. The actual power of GPT is running on OpenAI's cloud behind this API, not on your computer!\n",
"\n",
"OpenAI was so popular, that lots of other AI providers provided identical web endpoints, so you could use the same approach.\n",
"\n",
"So Ollama has an endpoint running on your local box at http://localhost:11434/v1/chat/completions \n",
"And in week 2 we'll discover that lots of other providers do this too, including Gemini and DeepSeek.\n",
"\n",
"And then the team at OpenAI had a great idea: they can extend their client library so you can specify a different 'base url', and use their library to call any compatible API.\n",
"\n",
"That's it!\n",
"\n",
"So when you say: `ollama_via_openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')` \n",
"Then this will make the same endpoint calls, but to Ollama instead of OpenAI."
]
},
{
"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 os\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0bd2aea1-d7d7-499f-b704-5b13e2ddd23f",
"metadata": {},
"outputs": [],
"source": [
"MODEL = \"llama3.2\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6df3141a-0a46-4ff9-ae73-bf8bee2aa3d8",
"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\n",
" \"\"\"\n",
" url: str\n",
" title: str\n",
" text: str\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)\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": "df2ea48b-7343-47be-bdcb-52b63a4de43e",
"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": "80f1a534-ae2a-4283-83cf-5e7c5765c736",
"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": "code",
"execution_count": null,
"id": "5dfe658d-e3f9-4b32-90e6-1a523f47f836",
"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": "2e2a09d0-bc47-490e-b085-fe3ccfbd16ad",
"metadata": {},
"outputs": [],
"source": [
"# And now: call the Ollama function instead of OpenAI\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']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "340e08a2-86f0-4cdd-9188-da2972cae7a6",
"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": "55e4790a-013c-40cf-9dff-bb5ec1d53964",
"metadata": {},
"outputs": [],
"source": [
"display_summary(\"https://zhufqiu.com\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8a96cbad-1306-4ce1-a942-2448f50d6751",
"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": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

202
week1/community-contributions/week1-EXERCISE-openai-ollama-tech-assistant.ipynb Normal file
View File

@@ -0,0 +1,202 @@
{
"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",
"\n",
"import os\n",
"from dotenv import load_dotenv\n",
"from IPython.display import Markdown, display, update_display\n",
"from openai import OpenAI\n",
"import ollama"
]
},
{
"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",
"\n",
"load_dotenv(override=True)\n",
"api_key = os.getenv('OPENAI_API_KEY')\n",
"\n",
"# Check the key\n",
"\n",
"if not api_key:\n",
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
"elif not api_key.startswith(\"sk-proj-\"):\n",
" print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
"elif api_key.strip() != api_key:\n",
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
"else:\n",
" print(\"API key found and looks good so far!\")\n",
"\n",
"openai = OpenAI()"
]
},
{
"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\n",
"\n",
"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": "1f879b7e-5ecc-4ec6-b269-78b6e2ed3480",
"metadata": {},
"outputs": [],
"source": [
"# prompts\n",
"\n",
"system_prompt = \"You are a helpful tutor who answers technical questions about programming code(especially python code), software engineering, data science and LLMs\"\n",
"user_prompt = \"Please give a detailed explanation to the following question: \" + question"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ac74ae5-af61-4a5d-b991-554fa67cd3d1",
"metadata": {},
"outputs": [],
"source": [
"messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\"role\": \"user\", \"content\": user_prompt}\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 = openai.chat.completions.create(\n",
" model=MODEL_GPT,\n",
" messages=messages,\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": "8f7c8ea8-4082-4ad0-8751-3301adcf6538",
"metadata": {},
"outputs": [],
"source": [
"# Get Llama 3.2 to answer\n",
"\n",
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n",
"HEADERS = {\"Content-Type\": \"application/json\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bd10d96-ee72-4c86-acd8-4fa417c25960",
"metadata": {},
"outputs": [],
"source": [
"!ollama pull llama3.2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d889d514-0478-4d7f-aabf-9a7bc743adb1",
"metadata": {},
"outputs": [],
"source": [
"stream = ollama.chat(model=MODEL_LLAMA, messages=messages, stream=True)\n",
"\n",
"response = \"\"\n",
"display_handle = display(Markdown(\"\"), display_id=True)\n",
"for chunk in stream:\n",
" response += chunk.get(\"message\", {}).get(\"content\", \"\")\n",
" response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
" update_display(Markdown(response), display_id=display_handle.display_id)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "452d442a-f3b0-42ad-89d2-a8dc664e8bb6",
"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": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}