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.
221 lines
6.4 KiB
221 lines
6.4 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": 1, |
|
"id": "c1070317-3ed9-4659-abe3-828943230e03", |
|
"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, update_display\n", |
|
"from openai import OpenAI" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# constants\n", |
|
"\n", |
|
"MODEL_GPT = 'gpt-4o-mini'\n", |
|
"MODEL_LLAMA = 'llama3.2'\n", |
|
"\n", |
|
"OLLAMA_API = \"http://localhost:11434/v1\"\n", |
|
"HEADERS = {\"Content-Type\": \"application/json\"}" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"API key looks good so far\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# set up environment\n", |
|
"\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", |
|
" " |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 4, |
|
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# here is the system prompt and payloads;\n", |
|
"\n", |
|
"system_prompt = \"\"\"\n", |
|
"You are an expert on LLMs and writing python code. You are able to answer complex questions with\n", |
|
"detailed answers and explain what every line of code does. You can refactor the code when asked.\n", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 7, |
|
"id": "60ce7000-a4a5-4cce-a261-e75ef45063b4", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Function to get answer, with streaming\n", |
|
"\n", |
|
"def llm_copilot(question, model):\n", |
|
" if 'llama' in model.lower():\n", |
|
" openai = OpenAI(base_url=OLLAMA_API, api_key='ollama')\n", |
|
" else:\n", |
|
" openai = OpenAI()\n", |
|
" \n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=model,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": question}\n", |
|
" ],\n", |
|
" stream=True\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": 8, |
|
"id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"Here's a revised version of your code:\n", |
|
"\n", |
|
"python\n", |
|
"if 'llama' in model.lower():\n", |
|
"\n", |
|
"\n", |
|
"OR if you want to keep the original style, you can modify it as follows:\n", |
|
"\n", |
|
"python\n", |
|
"if model.split('.')[-1] == 'llama3.2':\n", |
|
"\n", |
|
"\n", |
|
"In this second example, we use string indexing (`-1`) to get the last part of the `model` string after splitting at the dot (`.`) character.\n", |
|
"\n", |
|
"The first revised version uses Python's built-in string method `lower()` to convert `model` to lowercase and then checks if 'llama' is present in it. It returns True if the text contains \"llama\", otherwise, it will return False. \n", |
|
"\n", |
|
"However, both of these codes are using lazy evaluation, which means if you do this check inside a loop:\n", |
|
"\n", |
|
"python\n", |
|
"for i in range(100):\n", |
|
" print('llama')\n", |
|
"\n", |
|
"\n", |
|
"Python will use 'a' instead of 'llame' most of the time until `i == 98` because it has to wait for the condition to be met (and also does some lookup and look-around). If you want a case-insensitive search without this slowness, consider using a regular expression as shown below\n", |
|
"\n", |
|
"python\n", |
|
"import re\n", |
|
"\n", |
|
"if re.search(r' llama.', model):\n", |
|
"\n", |
|
"\n", |
|
"And if you still want that specific code structure, then use `replace` function as follows:\n", |
|
"\n", |
|
"python\n", |
|
"model = model.replace('llama', '')\n", |
|
"if model == '3.2':\n" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
}, |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"None\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# Ask question\n", |
|
"question = \"\"\"\n", |
|
"Change this code to check for just the 'llama' portion of text instead of the entire string:\n", |
|
"if model == 'llama3.2':\n", |
|
"\"\"\"\n", |
|
"\n", |
|
"print(llm_copilot(question, MODEL_LLAMA))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "1a4026cd-8967-4961-b26b-e3997307c4ba", |
|
"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 |
|
}
|
|
|