{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "fdc2f470", "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", "from openai import OpenAI\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": "5f0fbd79", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "API key found and looks good so far!\n" ] } ], "source": [ "# Load environment variables in a file called .env\n", "\n", "load_dotenv(override=True)\n", "api_key = os.getenv('OPENAI_API_KEY')\n", "\n", "# Check the 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 - see troubleshooting notebook\")\n", "else:\n", " print(\"API key found and looks good so far!\")\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "b771480a", "metadata": {}, "outputs": [], "source": [ "openai = OpenAI()" ] }, { "cell_type": "code", "execution_count": 4, "id": "0e97974c", "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": 5, "id": "2ec62fb3", "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 list of the flights available according to what user asks for, ignoring text that might be navigation related. \\\n", "Respond in markdown.\"" ] }, { "cell_type": "code", "execution_count": 6, "id": "7a93a605", "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 list of all the flights available in a table format in markdown. The columns of the table should be - Flight carrier, Flight Dat and times, Fare, No. of stops. \\\n", "Provide exact flight carriers. If it includes ads or offers, then summarize these too.\\n\\n\"\n", " user_prompt += website.text\n", " return user_prompt" ] }, { "cell_type": "code", "execution_count": 7, "id": "597646e5", "metadata": {}, "outputs": [], "source": [ "def fetch_flights(from_tx,to_tx, date_from,date_to=''):\n", " website = Website(f\"https://www.ca.kayak.com/flights/{from_tx}-{to_tx}/{date_from}/{date_to}\")\n", " user_prompt = user_prompt_for(website)\n", " messages = [{\"role\":\"system\",\"content\":system_prompt},{\"role\":\"user\",\"content\":user_prompt}]\n", " response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", " display(Markdown(response.choices[0].message.content))" ] }, { "cell_type": "code", "execution_count": 8, "id": "47ae61f3", "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "Here is the list of available flights from YYZ to DEL on 9/11:\n", "\n", "| Flight Carrier | Flight Date and Times | Fare | No. of Stops |\n", "|----------------|-----------------------|--------|--------------|\n", "| Air Canada | 9/11, 10:00 AM | C$ 833 | 1 |\n", "| Lufthansa | 9/11, 5:00 PM | C$ 847 | 2 |\n", "| Qatar Airways | 9/11, 1:30 PM | C$ 1,559| 1 |\n", "\n", "### Summary of Offers\n", "- The cheapest fare is C$ 833 with a travel time of 23 hours and 35 minutes.\n", "- The best fare option is C$ 847 with a travel time of 22 hours and 20 minutes.\n", "- The quickest option is priced at C$ 1,559 with a travel duration of 13 hours and 55 minutes. \n", "\n", "*Note: Prices are per person and do not include baggage fees.*" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fetch_flights('yyz','del','2025-11-09')" ] }, { "cell_type": "code", "execution_count": null, "id": "3a48ceb6", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "15bb1a04", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "902975bf", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "venv", "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": "3.12.11" } }, "nbformat": 4, "nbformat_minor": 5 }