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.
357 lines
9.4 KiB
357 lines
9.4 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "d5ce5658-9ba9-487c-bb31-f9030039990e", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"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\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "eec2b3ad-7b6f-4fe1-9e38-9ddbacf6adc6", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"load_dotenv(override=True)\n", |
|
"api_key=os.getenv(\"OPENAI_API_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\")\n", |
|
"else:\n", |
|
" print(\"API key found and looks good so far!\") " |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "fbb17244-b2b6-4494-969a-e0192115ef96", |
|
"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": "642d7ffb-94a9-40c5-bf1f-9bc4570efb58", |
|
"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": "c90b4384-1a4b-4cad-8d3d-331c46d4c7f1", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Create a messages list using the same format that we used for OpenAI\n", |
|
"\n", |
|
"messages = [\n", |
|
" {\"role\": \"user\", \"content\": \"Describelangflow\"}\n", |
|
"]" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "9c604ab2-6c25-4c2f-a6a2-60540ff74ca0", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"payload = {\n", |
|
" \"model\": MODEL,\n", |
|
" \"messages\": messages,\n", |
|
" \"stream\": False\n", |
|
" }" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "5629b49f-6ca9-466f-ad60-4d40a3b15321", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n", |
|
"print(response.json()['message']['content'])" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "5a88d730-1c7b-4e1e-b143-5a630a2f52bd", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"import ollama\n", |
|
"\n", |
|
"response = ollama.chat(model=MODEL, messages=messages)\n", |
|
"print(response['message']['content'])" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "62155b78-de4a-435b-867b-35b6c4b21f48", |
|
"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": "cd93d7b6-916a-45b8-9dfe-822a15c9a501", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"ed = Website(\"https://edwarddonner.com\")\n", |
|
"print(ed.title)\n", |
|
"print(ed.text)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "eea40735-c580-4d25-9317-c951e53faceb", |
|
"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", |
|
" response = ollama.chat(\n", |
|
" model = \"llama3.2\",\n", |
|
" messages = messages_for(website)\n", |
|
" )\n", |
|
" return response['message']['content']" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "cf844513-2b74-4306-9328-573d4996b772", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"summarize(\"https://edwarddonner.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "f5c35dfb-d38d-4c59-85ed-e7551175268b", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"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": "ca1fa5e7-44ce-45ae-a2ff-c38bc239f101", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"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 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": "52b5a899-3f96-4e45-849b-bba4a3f848de", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"print(user_prompt_for(ed))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "f11f9d7d-8eb5-410b-b27c-a3e086d5bf59", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"messages = [\n", |
|
" {\"role\": \"system\", \"content\": \"You are a snarky assistant\"},\n", |
|
" {\"role\": \"user\", \"content\": \"What is 2 + 2?\"}\n", |
|
"]" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "56c19a9c-4c69-4b6d-b9ac-c3b884efb8b1", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
" response = ollama.chat(\n", |
|
" model = \"llama3.2\",\n", |
|
" messages = messages\n", |
|
" )\n", |
|
" print(response['message']['content'])" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "0c05859c-4978-4b32-b971-0ea5d0147f00", |
|
"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": "a33dd65c-01f9-4a51-bc44-74427eafef42", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"messages_for(ed)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "a5593d92-2f3c-44c8-abdd-9089f04ce171", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def summarize(url):\n", |
|
" website = Website(url)\n", |
|
" response = ollama.chat(\n", |
|
" model = \"llama3.2\",\n", |
|
" messages = messages_for(website)\n", |
|
" )\n", |
|
" return response['message']['content']" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "6f75cc47-c03e-42fd-acdf-e980031c9976", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"summarize(\"https://edwarddonner.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "2d156ede-c20f-4569-997f-cd61e7b9c667", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def display_summary(url):\n", |
|
" summary = summarize(url)\n", |
|
" display(Markdown(summary))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "81f3d230-ed53-400f-b215-2ef9f6a92935", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"display_summary(\"https://edwarddonner.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "e17cd862-44e5-4af9-9dcc-7ee3d489a45d", |
|
"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 |
|
}
|
|
|