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.
213 lines
5.9 KiB
213 lines
5.9 KiB
{ |
|
"cells": [ |
|
{ |
|
"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": "4bdcd35a", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"!ollama pull deepseek-r1:8b" |
|
] |
|
}, |
|
{ |
|
"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": "1c106420", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# imports\n", |
|
"\n", |
|
"import requests\n", |
|
"import ollama\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "22d62f00", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Constants\n", |
|
"\n", |
|
"OLLAMA_API = \"http://localhost:11434/api/chat\"\n", |
|
"HEADERS = {\"Content-Type\": \"application/json\"}\n", |
|
"MODEL = \"deepseek-r1:8b\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "6de38216-6d1c-48c4-877b-86d403f4e0f8", |
|
"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": "4449b7dc", |
|
"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": "daca9448", |
|
"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": "0ec9d5d2", |
|
"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": "6e1ab04a", |
|
"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 = MODEL,\n", |
|
" messages = messages_for(website)\n", |
|
" )\n", |
|
" return response['message']['content']" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "0d3b5628", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def display_summary(url):\n", |
|
" summary = summarize(url)\n", |
|
" display(Markdown(summary))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "938e5633", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"display_summary(\"https://edwarddonner.com\")" |
|
] |
|
} |
|
], |
|
"metadata": { |
|
"kernelspec": { |
|
"display_name": "llms", |
|
"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 |
|
}
|
|
|