{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "135717e7",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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",
    "import ollama"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "29a9e634",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# OPTION 1\n",
    "# using openai\n",
    "\n",
    "# message = \"Hello, GPT! This is my first ever message to you! Hi!\"\n",
    "# client = OpenAI(base_url=\"http://localhost:11434/v1\", api_key=\"not-needed\")\n",
    "# response = openai.chat.completions.create(model=`<name of model>`, messages=[{\"role\":\"user\", \"content\":message}])\n",
    "# print(response.choices[0].message.content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "306993ed",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# OPTION 2\n",
    "# using Ollama\n",
    "\n",
    "message = \"Hello, GPT! This is my first ever message to you! Hi!\"\n",
    "model=\"llama3\"\n",
    "response=ollama.chat(model=model,messages=[{\"role\":\"user\",\"content\":message}])\n",
    "print(response[\"message\"][\"content\"])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "856f767b",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": "4ce558dc",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "# Let's try one out. Change the website and add print statements to follow along.\n",
    "\n",
    "ed = Website(\"https://edwarddonner.com\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5e3956f8",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": 7,
   "id": "99d791b4",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": 8,
   "id": "5d89b748",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": 9,
   "id": "9a97d3e2",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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(model=model,messages=messages_for(website))\n",
    "    return(response[\"message\"][\"content\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ec13fe0a",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "summarize(\"https://edwarddonner.com\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "e3ade092",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": null,
   "id": "be2d49e6",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "display_summary(\"https://edwarddonner.com\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1ccbf33b",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "display_summary(\"https://cnn.com\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ae3d0eae",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "display_summary(\"https://anthropic.com\")"
   ]
  }
 ],
 "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": "3.11.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}