Merge pull request #299 from ken-027/main

Week 1 Contribution to the LLM Engineering Course

week1/community-contributions/day2_exercise.ipynb

@@ -0,0 +1,274 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41136d6f-07bc-4f6f-acba-784b8e5707b1",
+   "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": "8612b4f7-5c31-48f3-8423-261914509617",
+   "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": "508bd442-7860-4215-b0f2-57f7adefd807",
+   "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": "cc7e8ada-4f8d-4090-be64-4aa72e03ac58",
+   "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": "4afd2e56-191a-4e31-949e-9b9376a39b5a",
+   "metadata": {
+    "scrolled": true
+   },
+   "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": "code",
+   "execution_count": null,
+   "id": "365f3d83-2601-42fb-89cc-98a4e1f79e0d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message = \"Hello, GPT! This is my first ever message to you! Hi!\"\n",
+    "response = ollama_via_openai.chat.completions.create(model=MODEL, messages=[{\"role\":\"user\", \"content\":message}])\n",
+    "print(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29c383ae-bf5b-41bc-b5af-a22f851745dc",
+   "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": "dc61e30f-653f-4554-b1cd-6e61a0e2430a",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "ed = Website(\"https://edwarddonner.com\")\n",
+    "print(ed.title)\n",
+    "print(ed.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db2066fb-3079-4775-832a-dcc0f19beb6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\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": "af81b070-b6fe-4b18-aa0b-c03cd76a0adf",
+   "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": "4e66291b-23b1-4915-b6a3-11a4b6a4db66",
+   "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": "67c92f47-4a3b-491f-af00-07fda470087e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "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": "db1b9085-e5e7-4ec9-a264-acc389085ada",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages_for(ed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "677bfc2f-19ac-46a0-b67e-a2b2ddf9cf6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def summarize(url):\n",
+    "    website = Website(url)\n",
+    "    response = ollama_via_openai.chat.completions.create(\n",
+    "        model = MODEL,\n",
+    "        messages = messages_for(website)\n",
+    "    )\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee3242ba-b695-4b1e-8a91-2fdeb536c2e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "summarize(\"https://edwarddonner.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85142cb8-ce0c-4c31-8b26-bb1744cf99ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def display_summary(url):\n",
+    "    summary = summarize(url)\n",
+    "    display(Markdown(summary))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63db51a7-dd03-4514-8954-57156967f82c",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "display_summary(\"https://app.daily.dev/posts/bregman-arie-devops-exercises-linux-jenkins-aws-sre-prometheus-docker-python-ansible-git-k-yli9wthnf\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:base] *",
+   "language": "python",
+   "name": "conda-base-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}