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.
180 lines
4.9 KiB
180 lines
4.9 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", |
|
"import ollama" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# constants\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", |
|
"load_dotenv(override=True)\n", |
|
"api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"\n", |
|
"if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n", |
|
" print(\"API key looks good so far\")\n", |
|
"else:\n", |
|
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n", |
|
"\n", |
|
"openai = OpenAI()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"system_prompt = \"You are provided with a technical question. \\\n", |
|
"You are answering by providing a quick explanation and giving some examples.\\n\"\n", |
|
"\n", |
|
"# here is the question; type over this to ask something new\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": "60ce7000-a4a5-4cce-a261-e75ef45063b4", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Get gpt-4o-mini to answer, with streaming\n", |
|
"def get_answer_gpt():\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=MODEL_GPT,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": question}\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": "8f7c8ea8-4082-4ad0-8751-3301adcf6538", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Get Llama 3.2 to answer\n", |
|
"def get_answer_ollama():\n", |
|
" stream = ollama.generate(\n", |
|
" MODEL_LLAMA,\n", |
|
" question,\n", |
|
" stream=True\n", |
|
" )\n", |
|
" \n", |
|
" response = \"\"\n", |
|
" display_handle = display(Markdown(\"\"), display_id=True)\n", |
|
" for chunk in stream:\n", |
|
" response += chunk['response'] 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": "4a859eb1-23fa-40dd-ba91-b35084433a00", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"get_answer_gpt()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "1c73f046-da3a-49a5-8a74-4b8a86a9032a", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"get_answer_ollama()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "bea20f33-a710-44ab-9a4d-856db05e4201", |
|
"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 |
|
}
|
|
|