{ "cells": [ { "cell_type": "code", "execution_count": null, "id": "d25b0aef-3e5e-4026-90ee-2b373bf262b7", "metadata": {}, "outputs": [], "source": [ "# Step 0: Import Libraries\n", "from bs4 import BeautifulSoup\n", "from IPython.display import Markdown, display\n", "import ollama\n", "from openai import OpenAI\n", "import requests\n", "\n", "# Step 1: Set Constants and Variables\n", "print(\"[INFO] Setting constants and variable ...\")\n", "WEBSITE_URL = \"https://arxiv.org/\"\n", "MODEL = \"llama3.2\"\n", "approaches = [\"local-call\", \"python-package\", \"openai-python-library\"]\n", "approach = approaches[2]\n", "\n", "# Step 1: Scrape Website\n", "print(\"[INFO] Scraping website ...\")\n", "url_response = requests.get(\n", " url=WEBSITE_URL,\n", " headers={\"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", "soup = BeautifulSoup(\n", " markup=url_response.content,\n", " features=\"html.parser\"\n", " )\n", "website_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", "website_text = soup.body.get_text(\n", " separator=\"\\n\",\n", " strip=True\n", " )\n", "\n", "# Step 2: Create Prompts\n", "print(\"[INFO] Creating system prompt ...\")\n", "system_prompt = \"You are an assistant that analyzes the contents of a \\\n", " website and provides a short summary, ignoring text that might be \\\n", " navigation related. Respond in markdown.\"\n", "\n", "print(\"[INFO] Creating user prompt ...\")\n", "user_prompt = f\"You are looking at a website titled {website_title}\"\n", "user_prompt += \"\\nBased on the contents of the website, please provide \\\n", " a short summary of this website in markdown. If the website \\\n", " includes news or announcements, summarize them, too. The contents \\\n", " of this website are as follows:\\n\\n\"\n", "user_prompt += website_text\n", "\n", "# Step 3: Make Messages List\n", "print(\"[INFO] Making messages list ...\")\n", "messages = [\n", " {\"role\": \"system\", \"content\": system_prompt},\n", " {\"role\": \"user\", \"content\": user_prompt}\n", "]\n", "\n", "# Step 4: Call Model and Print Results\n", "if approach == \"local-call\":\n", " response = requests.post(\n", " url=\"http://localhost:11434/api/chat\",\n", " json={\n", " \"model\": MODEL,\n", " \"messages\": messages,\n", " \"stream\": False\n", " },\n", " headers={\"Content-Type\": \"application/json\"}\n", " )\n", " print(\"[INFO] Printing result ...\")\n", " display(Markdown(response.json()[\"message\"][\"content\"]))\n", "elif approach == \"python-package\":\n", " response = ollama.chat(\n", " model=MODEL,\n", " messages=messages,\n", " stream=False\n", " )\n", " print(\"[INFO] Printing result ...\")\n", " display(Markdown(response[\"message\"][\"content\"]))\n", "elif approach == \"openai-python-library\":\n", " ollama_via_openai = OpenAI(\n", " base_url=\"http://localhost:11434/v1\",\n", " api_key=\"ollama\"\n", " )\n", " response = ollama_via_openai.chat.completions.create(\n", " model=MODEL,\n", " messages=messages\n", " )\n", " print(\"[INFO] Printing result ...\")\n", " display(Markdown(response.choices[0].message.content))\n", "else:\n", " raise ValueError(f\"[INFO] Invalid approach! Please select an approach from {approaches} and try again.\")" ] }, { "cell_type": "code", "execution_count": null, "id": "b0a6676e-fb43-4725-9389-2acd74c13c4e", "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": "3.12.8" } }, "nbformat": 4, "nbformat_minor": 5 }