From 99704cb24726634217586bdfef10369300fe8ae3 Mon Sep 17 00:00:00 2001 From: joluesi Date: Sat, 12 Apr 2025 20:13:15 +0200 Subject: [PATCH] Ejercicio 2 - Semana 1 - Scrapper con Ollama --- week1/myWebScrIApper.ipynb | 246 +++++++++++++++++++++++++++++++++++++ 1 file changed, 246 insertions(+) create mode 100644 week1/myWebScrIApper.ipynb diff --git a/week1/myWebScrIApper.ipynb b/week1/myWebScrIApper.ipynb new file mode 100644 index 0000000..d56c45f --- /dev/null +++ b/week1/myWebScrIApper.ipynb @@ -0,0 +1,246 @@ +{ + "cells": [ + { + "cell_type": "raw", + "id": "309296ff-f0c2-4e31-986c-b6e779ad17cd", + "metadata": {}, + "source": [ + "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": 1, + "id": "62b6082c-67d0-4ebc-97a2-8b7ee61e0294", + "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\n", + "import ollama\n", + "\n", + "# If you get an error running this cell, then please head over to the troubleshooting notebook!" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "1e048442-d95c-4017-b0ee-34966e8b5452", + "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": 3, + "id": "6c7d475d-b1bb-4d99-94af-2435593a9aff", + "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": 4, + "id": "7bedc3b2-01b6-41c2-b0a3-4f2d8f5772aa", + "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": 17, + "id": "23fcb3fc-af67-44f3-8f2a-475d1c7e7a69", + "metadata": {}, + "outputs": [], + "source": [ + "# 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" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "b3f57f88-f5c9-42f8-8200-9a33c3ea8348", + "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": 7, + "id": "3922e700-1695-4dfb-8004-fe9356178056", + "metadata": {}, + "outputs": [], + "source": [ + "def message_payload(website):\n", + " url = Website(website)\n", + " payload = {\n", + " \"model\": MODEL,\n", + " \"messages\": messages_for(url),\n", + " \"stream\": False\n", + " }\n", + " return payload" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "97e99c58-4a71-4c2c-9255-1b676446e37b", + "metadata": {}, + "outputs": [], + "source": [ + "# And now: call the OpenAI API. You will get very familiar with this!\n", + "\n", + "def summarize(url):\n", + " payload = message_payload(url)\n", + " response = requests.post(OLLAMA_API, json=payload, headers=HEADERS)\n", + " return response.json()['message']['content']" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "742d3b5b-c7bd-40c3-a75e-863d1e9f6caa", + "metadata": {}, + "outputs": [], + "source": [ + "# 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": "code", + "execution_count": 18, + "id": "08332604-9de0-4cac-a9cd-7591ec10d66b", + "metadata": {}, + "outputs": [ + { + "data": { + "text/markdown": [ + "**Resumen del sitio web**\n", + "\n", + "El sitio web Plataforma para fórex y las bolsas de valores: MetaTrader 5 es una plataforma comercial destinada a los traders de forex, acciones y otros activos financieros. La plataforma ofrece una variedad de herramientas y características, incluyendo gráficos, análisis técnico y fundamental, alertas y servicios comerciales.\n", + "\n", + "**Noticias**\n", + "\n", + "* MetaQuotes presentará sus últimas novedades en la iFX Expo de México del 9 al 10 de abril.\n", + "* El bróker global regulado ha ampliado significativamente la gama de herramientas disponibles para los tráders con MetaTrader 5 Automations.\n", + "* MetaTrader 5 ha sido premiada como la mejor plataforma comercial multimercado en la feria de Ciudad de México.\n", + "* La aplicación móvil MetaTrader 5 para iOS ha recibido una actualización con características nuevas, incluyendo objetos de texto para gráficos y temporizador de barras.\n", + "\n", + "**Características destacadas**\n", + "\n", + "* Trading móvil con aplicaciones para iPhone/iPad y Android\n", + "* Señales comerciales y copiado de operaciones\n", + "* Servicios comerciales y alertas\n", + "* Gráficos y análisis técnico y fundamental\n", + "* Entorno de desarrollo MQL5 y lenguaje de programación MQL5\n", + "* Virtual hosting (VPS) y trading automatizado\n", + "\n", + "**Servicios**\n", + "\n", + "* Descarga de la plataforma MetaTrader 5\n", + "* Comprar la plataforma MetaTrader 5\n", + "* Conexión a la plataforma web y tradere automatizado\n", + "* Acceso a la comunidad de traders y recursos educativos" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_summary(\"https://www.metatrader5.com/es\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "adb000a9-e2ba-48cc-bb87-1b75db2d9707", + "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 +}