Merge pull request #643 from gg-lol-123/community-contributions-branch

Added Business_Brochure_project notebook to community-contributions

week1/community-contributions/Business_Brochure_project-Copy1.ipynb

@@ -0,0 +1,425 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d5b08506-dc8b-4443-9201-5f1848161363",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "import os\n",
+    "import requests\n",
+    "import json\n",
+    "from typing import List\n",
+    "from dotenv import load_dotenv\n",
+    "from bs4 import BeautifulSoup\n",
+    "from IPython.display import Markdown, display, update_display\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ce95b0e-3f98-4cef-b9fe-d963fdeeed2d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# run ollama serve in your Anaconda terminal\n",
+    "MODEL = \"llama3.2\"\n",
+    "openai = OpenAI(base_url=\"http://localhost:11434/v1\", api_key=\"ollama\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "106dd65e-90af-4ca8-86b6-23a41840645b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# A class to represent a Webpage\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",
+    "    A utility class to represent a Website that we have scraped, now with links\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def __init__(self, url):\n",
+    "        self.url = url\n",
+    "        response = requests.get(url, headers=headers)\n",
+    "        self.body = response.content\n",
+    "        soup = BeautifulSoup(self.body, 'html.parser')\n",
+    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
+    "        if soup.body:\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",
+    "        else:\n",
+    "            self.text = \"\"\n",
+    "        links = [link.get('href') for link in soup.find_all('a')]\n",
+    "        self.links = [link for link in links if link]\n",
+    "\n",
+    "    def get_contents(self):\n",
+    "        return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e30d8128-933b-44cc-81c8-ab4c9d86589a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ed = Website(\"https://edwarddonner.com\")\n",
+    "ed.links"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6957b079-0d96-45f7-a26a-3487510e9b35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n",
+    "You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n",
+    "such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n",
+    "link_system_prompt += \"You should respond in JSON as in these examples:\"\n",
+    "link_system_prompt += \"\"\"example 1:\n",
+    "{\n",
+    "    \"links\": [\n",
+    "        {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n",
+    "        {\"type\": \"careers page\", \"url\": \"https://another.full.url/careers\"}]}\n",
+    "\n",
+    "Example 2:\n",
+    "    {\"links\": [{\"type\": \"about page\", \"url\": \"https://great-comps.de/about-me\"},\n",
+    "            {\"type\": \"news page\": \"url\": \"https://great-comps.de/news\"},\n",
+    "            {\"type\": \"case studies page\": \"url\": \"https://great-comps.de/case-studies\"},\n",
+    "            {\"type\": \"workshop page\": \"url\": \"https://great-comps.de/workshop-ai\"},]}\n",
+    "\n",
+    "\n",
+    "Example 3:\n",
+    "    {\"links\": [{\"type\": \"über mich\", \"url\": \"https://wahlen-robbie.at/ueber-mich\"},\n",
+    "            {\"type\": \"aktuelles\": \"url\": \"https://wahlen-robbie.at/neuigkeiten\"},\n",
+    "            {\"type\": \"whitepaper\": \"url\": \"https://wahlen-robbie.at/whitepapers\"},\n",
+    "            {\"type\": \"services\": \"url\": \"https://wahlen-robbie.at/services\"}]}\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b97e4068-97ed-4120-beae-c42105e4d59a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(link_system_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_links_user_prompt(website):\n",
+    "    user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n",
+    "    user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n",
+    "Do not include Terms of Service, Privacy, email links.\\n\"\n",
+    "    user_prompt += \"Links (some might be relative links):\\n\"\n",
+    "    user_prompt += \"\\n\".join(website.links)\n",
+    "    return user_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6bcbfa78-6395-4685-b92c-22d592050fd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(get_links_user_prompt(ed))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a29aca19-ca13-471c-a4b4-5abbfa813f69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_links(url):\n",
+    "    website = Website(url)\n",
+    "    response = openai.chat.completions.create(\n",
+    "        model=MODEL,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": link_system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n",
+    "      ],\n",
+    "        response_format={\"type\": \"json_object\"}\n",
+    "    )\n",
+    "    result = response.choices[0].message.content\n",
+    "    return json.loads(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74a827a0-2782-4ae5-b210-4a242a8b4cc2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Getting the links for HuggingFace\n",
+    "huggingface = Website(\"https://huggingface.co\")\n",
+    "huggingface.links"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "get_links(\"https://huggingface.co\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_all_details(url):\n",
+    "    result = \"Landing page:\\n\"\n",
+    "    result += Website(url).get_contents()\n",
+    "    links = get_links(url)\n",
+    "    #print(\"Found links:\", links)\n",
+    "    for link in links[\"links\"]:\n",
+    "        result += f\"\\n\\n{link['type']}\\n\"\n",
+    "        result += Website(link[\"url\"]).get_contents()\n",
+    "    return result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5099bd14-076d-4745-baf3-dac08d8e5ab2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(get_all_details(\"https://edwarddonner.com\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
+    "and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
+    "Include details of company culture, customers and careers/jobs if you have the information.\"\n",
+    "\n",
+    "# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n",
+    "\n",
+    "# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n",
+    "# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n",
+    "# Include details of company culture, customers and careers/jobs if you have the information.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_brochure_user_prompt(company_name, url):\n",
+    "    user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n",
+    "    user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n",
+    "    user_prompt += get_all_details(url)\n",
+    "    user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters\n",
+    "    return user_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd909e0b-1312-4ce2-a553-821e795d7572",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "get_brochure_user_prompt(\"ed\", \"https://edwarddonner.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_brochure(company_name, url):\n",
+    "    response = openai.chat.completions.create(\n",
+    "        model=MODEL,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
+    "          ],\n",
+    "    )\n",
+    "    result = response.choices[0].message.content\n",
+    "    display(Markdown(result))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e093444a-9407-42ae-924a-145730591a39",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "create_brochure(\"ed\", \"https://edwarddonner.com\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbc1a523-4c5c-4571-8541-456e5feed185",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_brochure_translated(company_name, url, language):\n",
+    "    system_prompt = f\"\"\"You are an expert professional translator. Translate the following brochure text into {language}.\n",
+    "    Make sure to translate into a idiomatic {language}, matching the users language's natural structure, wording and expressions,\n",
+    "    so it can't be recognised as a translation.\n",
+    "    Be sure to also maintain an appropriate tone, Output the translated brochure in Markdown format.\"\"\"\n",
+    "    response = openai.chat.completions.create(\n",
+    "        model=MODEL,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
+    "          ],\n",
+    "        \n",
+    "    )\n",
+    "    result = response.choices[0].message.content\n",
+    "    display(Markdown(result))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ff2ddc4-f13c-44b2-8043-d66f36b0954c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "create_brochure_translated(\"ed\", \"https://edwarddonner.com\", \"French\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18",
+   "metadata": {},
+   "source": [
+    "## Finally - a minor improvement\n",
+    "\n",
+    "With a small adjustment, we can change this so that the results stream back from OpenAI,\n",
+    "with the familiar typewriter animation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51db0e49-f261-4137-aabe-92dd601f7725",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def stream_brochure(company_name, url):\n",
+    "    stream = openai.chat.completions.create(\n",
+    "        model=MODEL,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
+    "          ],\n",
+    "        stream=True\n",
+    "    )\n",
+    "    \n",
+    "    response = \"\"\n",
+    "    display_handle = display(Markdown(\"\"), display_id=True)\n",
+    "    for chunk in stream:\n",
+    "        response += chunk.choices[0].delta.content or ''\n",
+    "        response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n",
+    "        update_display(Markdown(response), display_id=display_handle.display_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09f18581-b870-4952-8430-217afaf7a83e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def stream_brochure_translated(company_name, url, language):\n",
+    "    system_prompt = f\"\"\"You are an expert professional translator. \n",
+    "    Translate the following brochure text into {language}.\n",
+    "    Make sure to translate into idiomatic {language}, matching the natural structure, wording, and expressions.\n",
+    "    Maintain an appropriate tone. Output the translated brochure in Markdown format.\"\"\"\n",
+    "\n",
+    "    stream = openai.chat.completions.create(\n",
+    "        model=MODEL,\n",
+    "        messages=[\n",
+    "            {\"role\": \"system\", \"content\": system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n",
+    "        ],\n",
+    "        stream=True\n",
+    "    )\n",
+    "\n",
+    "    response = \"\"\n",
+    "    display_handle = display(Markdown(\"\"), display_id=True)\n",
+    "    for chunk in stream:\n",
+    "        response += chunk.choices[0].delta.content or ''\n",
+    "        # clean up formatting glitches while streaming\n",
+    "        response = response.replace(\"```\", \"\").replace(\"markdown\", \"\")\n",
+    "        update_display(Markdown(response), display_id=display_handle.display_id)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stream_brochure_translated(\"ed\", \"https://edwarddonner.com\", \"Spanish\")"
+   ]
+  }
+ ],
+ "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
+}