From 40c03edb5aaa67ce30b208ee7dc8b1d35827a2d7 Mon Sep 17 00:00:00 2001 From: Barry Northern Date: Mon, 13 Jan 2025 21:46:32 +0000 Subject: [PATCH] notebook for day2 exercise, summarize websites using ollama --- .../day2-ollama-website-summarizer.ipynb | 159 ++++++++++++++++++ 1 file changed, 159 insertions(+) create mode 100644 week1/community-contributions/day2-ollama-website-summarizer.ipynb diff --git a/week1/community-contributions/day2-ollama-website-summarizer.ipynb b/week1/community-contributions/day2-ollama-website-summarizer.ipynb new file mode 100644 index 0000000..2495f94 --- /dev/null +++ b/week1/community-contributions/day2-ollama-website-summarizer.ipynb @@ -0,0 +1,159 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "568fd96a-8cf6-42aa-b9cf-74b7aa383595", + "metadata": {}, + "source": [ + "# Ollama Website Summarizer\n", + "## Scrape websites and summarize them locally using Ollama\n", + "\n", + "This script is a complete example of the day 1 program, which uses OpenAI API to summarize websites, altered to use techniques from the day 2 exercise to call Ollama models locally." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a9502a0f-d7be-4489-bb7f-173207e802b6", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "\n", + "import ollama\n", + "import requests\n", + "from bs4 import BeautifulSoup\n", + "from IPython.display import Markdown, display\n", + "\n", + "MODEL = \"llama3.2\"\n", + "\n", + "# 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)\n", + " \n", + "# A function that writes a User Prompt that asks for summaries of websites:\n", + "\n", + "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\n", + " \n", + "# Create a messages list for a summarize prompt given a website\n", + "\n", + "def create_summarize_prompt(website):\n", + " return [\n", + " {\"role\": \"system\", \"content\": \"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.\" },\n", + " {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", + " ]\n", + "\n", + "# And now: call Ollama to summarize\n", + "\n", + "def summarize(url):\n", + " website = Website(url)\n", + " messages = create_summarize_prompt(website)\n", + " response = ollama.chat(model=MODEL, messages=messages)\n", + " return response['message']['content']\n", + " \n", + "# A function to display this nicely in the Jupyter output, using markdown\n", + "\n", + "def display_summary(url):\n", + " summary = summarize(url)\n", + " display(Markdown(summary))" + ] + }, + { + "cell_type": "markdown", + "id": "037627b0-b039-4ca4-a6d4-84ad8fc6a013", + "metadata": {}, + "source": [ + "## Pre-requisites\n", + "\n", + "Before we can run the script above, we need to make sure Ollama is running on your machine!\n", + "\n", + "Simply visit ollama.com and install!\n", + "\n", + "Once complete, the ollama server should already be running locally.\n", + "If you visit:\n", + "http://localhost:11434/\n", + "\n", + "You should see the message Ollama is running." + ] + }, + { + "cell_type": "markdown", + "id": "6c2d84fd-2a9b-476d-84ad-4b8522d47023", + "metadata": {}, + "source": [ + "## Run!\n", + "\n", + "Shift+Enter the code below to summarize a website.\n", + "\n", + "### NOTE!\n", + "\n", + "This will only work with websites that return HTML content, and may return unexpected results for SPAs that are created with JS." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "100829ba-8278-409b-bc0a-82ac28e1149f", + "metadata": {}, + "outputs": [], + "source": [ + "display_summary(\"https://edwarddonner.com/2024/11/13/llm-engineering-resources/\")" + ] + }, + { + "cell_type": "markdown", + "id": "ffe4e760-dfa6-43fa-89c4-beea547707ac", + "metadata": {}, + "source": [ + "Edit the URL above, or add code blocks of your own to try it out!" + ] + } + ], + "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 +}