diff --git a/week1/community-contributions/day1_coverletter_tailored_to_CV_and_job_description.ipynb b/week1/community-contributions/day1_coverletter_tailored_to_CV_and_job_description.ipynb new file mode 100644 index 0000000..9c63b6a --- /dev/null +++ b/week1/community-contributions/day1_coverletter_tailored_to_CV_and_job_description.ipynb @@ -0,0 +1,211 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "d955d75d-4970-48fe-983e-a2a850cecfc5", + "metadata": {}, + "outputs": [], + "source": [ + "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", + "import PyPDF2\n", + "from selenium import webdriver\n", + "from selenium.webdriver.chrome.options import Options\n", + "from selenium.webdriver.chrome.service import Service\n", + "from webdriver_manager.chrome import ChromeDriverManager\n", + "from bs4 import BeautifulSoup\n", + "import time" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6e1e5dd3-f91a-466b-8fd4-2dbf4eedf101", + "metadata": {}, + "outputs": [], + "source": [ + "load_dotenv(override = True)\n", + "api_key = os.getenv(\"OPENAI_API_KEY\")\n", + "\n", + "if not api_key:\n", + " print(\"No API key\")\n", + "elif not api_key.startswith(\"sk-proj-\"):\n", + " print(\"API key doesn't look correct, check it\")\n", + "elif api_key.strip() != api_key:\n", + " print(\"It looks like API key has an extra space - check it\")\n", + "else:\n", + " print(\"API key looks good, moving on!\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "67a6e583-1ef7-4b77-8886-c0e8c619933c", + "metadata": {}, + "outputs": [], + "source": [ + "openai = OpenAI()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "34a07806-dd68-4a86-8b6e-e1b2aaf0daa1", + "metadata": {}, + "outputs": [], + "source": [ + "# path to the CV\n", + "path = \"/Users/yanasklar/Documents/For applying/CV/СV_YanaSklyar_c.pdf\"\n", + "headers = {\n", + " \"User-Agent\": \"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36\"\n", + "}\n", + "\n", + "class Vacancy:\n", + " def __init__(self, url, instructions = \"\"):\n", + " self.url = url\n", + " \n", + " # configure Chrome settings\n", + " options = Options()\n", + " # options.add_argument(\"--headless\") \n", + " \"\"\"\n", + " Headless mode runs the browser in the background (invisible).\n", + " However, some websites (like openai.com) block headless browsers.\n", + " So if this line is active, the page may not load correctly and you may not get the full content.\n", + " \"\"\"\n", + " options.add_argument(\"--disable-gpu\")\n", + " options.add_argument(\"--no-sandbox\")\n", + " options.add_argument(\"--window-size=1920x1080\")\n", + "\n", + " # use webdriver-manager to manage ChromeDriver\n", + " service = Service(ChromeDriverManager().install())\n", + " driver = webdriver.Chrome(service=service, options=options)\n", + " driver.get(url)\n", + " time.sleep(3) # let the page load\n", + "\n", + " # take the source of the page\n", + " page_source = driver.page_source\n", + " driver.quit()\n", + "\n", + " # analyse with BeautifulSoup\n", + " soup = BeautifulSoup(page_source, 'html.parser')\n", + "\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " for irrelevant in soup.body([\"img\", \"script\", \"style\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator='\\n', strip=True)\n", + "\n", + " # read CV\n", + " with open(path, 'rb') as f:\n", + " reader = PyPDF2.PdfReader(f)\n", + " cv_text = \"\"\n", + " for page in reader.pages:\n", + " text = page.extract_text()\n", + " if text:\n", + " cv_text += text + \"\\n\"\n", + " self.cv_text = cv_text\n", + "\n", + " # summarise and print the description of the job\n", + " message = f\"\"\"Here is the content of a webpage: {self.text}.\n", + " Find job description on that page,\n", + " summarise it, include the list requirements and other important details.\n", + " \"\"\"\n", + " messages = [{\"role\":\"user\", \"content\":message}]\n", + " response = openai.chat.completions.create(model='gpt-4o-mini', messages = messages)\n", + " print(\"The job description: \", response.choices[0].message.content)\n", + "\n", + " # create prompts\n", + " self.system_prompt = \"\"\"You are a career assistant specializing in writing cover letter.\n", + " Your tasks:\n", + " 1. Read the candidate's CV (provided as text).\n", + " 2. Read the job description (provided from a webpage).\n", + " 3. Write a concise and compelling cover letter, that:\n", + " - Hightlights the most relevant experience and skills from the CV,\n", + " - Aligns directly wit the requirements in the job description,\n", + " - Adapts to cultural and professional norms in Israel.\n", + " The letter should be no longer than half a page, persuasive and tailored to make the applicant stand out.\n", + " \"\"\"\n", + "\n", + " user_prompt = f\"\"\"\n", + " Here is my CV:\n", + " {self.cv_text}\n", + " \n", + " The job vacancy is from the website {self.title}.\n", + " Here is the decription of the vacancy:\n", + " {self.text}\n", + " Please write a cover letter that connects my background to this vacancy.\n", + " Make it persuasive and suitable for Israeli job market.\n", + " \"\"\"\n", + " \n", + " if instructions:\n", + " user_prompt += f\"Additional instructions: {instructions}\"\n", + " self.user_prompt = user_prompt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9160b9f5-177b-4477-8e54-3a212f275a22", + "metadata": {}, + "outputs": [], + "source": [ + "def cover_letter(url, instructions = \"\"):\n", + " vacancy = Vacancy(url, instructions)\n", + " messages = [\n", + " {\"role\":\"system\", \"content\":vacancy.system_prompt},\n", + " {\"role\":\"user\", \"content\":vacancy.user_prompt}\n", + " ]\n", + " response = openai.chat.completions.create(model='gpt-4o-mini', messages=messages)\n", + " if not response:\n", + " print(\"smt went wrong\")\n", + " print(response.choices[0].message.content)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1de4b55c-a8da-445f-9865-c7a8bafdbc3c", + "metadata": {}, + "outputs": [], + "source": [ + "a = \"https://www.linkedin.com/jobs/view/4285898438/?alternateChannel=search&eBP=CwEAAAGY3R5LOabDLOVTy6xvBcSlWyAkIXQz8IRkSM3rgsqTPtvcEvUSnq980O7oLV2Hh_ldTpc2cBBmRq1IRnLtp7TzEcUvndFEXeCuviA5yo7oFYfW7KoEp4SPNzmf3D9LtnSgk9Iudy3skk6n3hVOtyDpx8Zm0AiTWPvdwCaZ_w5Xu8lAG797NRNDco71ynm99LmCOC9Go7DdDQ2eLewamc4SOsA4xWcXy0GmZVy3kBF1AprK3ylAYR2wrm5-hp4lRpbbfUxXjkEOG6H_GbPpKtN-N8mYnMd9w_cej5qQmTFX86gqSi6HuXFtK0h46TbOS5r-YQksVd1Yb4kYZnDznWXPLbxp04xVJSPzsHoa05wQdOfZ2UUSoMTJmic3n3qfV2u9Bp8n4sLYtINpzKdvm4eADGGkN-nR3O2oPeas9XjGbBwNdjXHAcX_PJoRwlFdQ1gVkYQEF1T7qAfXUJoUt-fv4oLxGnIgV6yJuMgw&refId=9NA7Bvt%2FhCqDkFNRGu1dPA%3D%3D&trackingId=W11hvpcIjHA%2FjU%2FFZ%2B1uAA%3D%3D\"\n", + "b = \"The style of the cover letter should informal, as if i talked to a friend about my background\"\n", + "cover_letter(a, b)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0feb3cbe-686a-4a97-9ca3-a0cb32a24c5d", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python (llms)", + "language": "python", + "name": "llms" + }, + "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 +}