diff --git a/week1/community-contributions/day1-resume-analyzer-for-job-postings.ipynb b/week1/community-contributions/day1-resume-analyzer-for-job-postings.ipynb new file mode 100644 index 0000000..f737667 --- /dev/null +++ b/week1/community-contributions/day1-resume-analyzer-for-job-postings.ipynb @@ -0,0 +1,316 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "1c6700cb-a0b0-4ac2-8fd5-363729284173", + "metadata": {}, + "source": [ + "# AI-Powered Resume Analyzer for Job Postings" + ] + }, + { + "cell_type": "markdown", + "id": "a2fa4891-b283-44de-aa63-f017eb9b140d", + "metadata": {}, + "source": [ + "This tool is designed to analyze resumes against specific job postings, offering valuable insights such as:\n", + "\n", + "- Identification of skill gaps\n", + "- Keyword matching between the CV and the job description\n", + "- Tailored recommendations for CV improvement\n", + "- An alignment score reflecting how well the CV fits the job\n", + "- Personalized feedback \n", + "- Job market trend insights\n", + "\n", + "An example of the tool's output can be found [here](https://tvarol.github.io/sideProjects/AILLMAgents/output.html)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8a6a34ea-191f-4c54-9793-a3eb63faab23", + "metadata": {}, + "outputs": [], + "source": [ + "# Imports\n", + "import os\n", + "import io\n", + "import time\n", + "import requests\n", + "import PyPDF2\n", + "from dotenv import load_dotenv\n", + "from IPython.display import Markdown, display\n", + "from openai import OpenAI\n", + "from ipywidgets import Textarea, FileUpload, Button, VBox, HTML" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "04bbe1d3-bacc-400c-aed2-db44699e38f3", + "metadata": {}, + "outputs": [], + "source": [ + "# Load environment variables\n", + "load_dotenv(override=True)\n", + "api_key = os.getenv('OPENAI_API_KEY')\n", + "\n", + "# Check the key\n", + "if not api_key:\n", + " print(\"No API key was found!!!\")\n", + "else:\n", + " print(\"API key found and looks good so far!\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "27bfcee1-58e6-4ff2-9f12-9dc5c1aa5b5b", + "metadata": {}, + "outputs": [], + "source": [ + "openai = OpenAI()" + ] + }, + { + "cell_type": "markdown", + "id": "c82e79f2-3139-4520-ac01-a728c11cb8b9", + "metadata": {}, + "source": [ + "## Using a Frontier Model GPT-4o Mini for This Project\n", + "\n", + "### Types of Prompts\n", + "\n", + "Models like GPT4o have been trained to receive instructions in a particular way.\n", + "\n", + "They expect to receive:\n", + "\n", + "**A system prompt** that tells them what task they are performing and what tone they should use\n", + "\n", + "**A user prompt** -- the conversation starter that they should reply to" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0da158ad-c3a8-4cef-806f-be0f90852996", + "metadata": {}, + "outputs": [], + "source": [ + "# Define our system prompt \n", + "system_prompt = \"\"\"You are a powerful AI model designed to assist with resume analysis. Your task is to analyze a resume against a given job posting and provide feedback on how well the resume aligns with the job requirements. Your response should include the following: \n", + "1) Skill gap identification: Compare the skills listed in the resume with those required in the job posting, highlighting areas where the resume may be lacking or overemphasized.\n", + "2) Keyword matching between a CV and a job posting: Match keywords from the job description with the resume, determining how well they align. Provide specific suggestions for missing keywords to add to the CV.\n", + "3) Recommendations for CV improvement: Provide actionable suggestions on how to enhance the resume, such as adding missing skills or rephrasing experience to match job requirements.\n", + "4) Alignment score: Display a score that represents the degree of alignment between the resume and the job posting.\n", + "5) Personalized feedback: Offer tailored advice based on the job posting, guiding the user on how to optimize their CV for the best chances of success.\n", + "6) Job market trend insights, provide broader market trends and insights, such as in-demand skills and salary ranges.\n", + "Provide responses that are concise, clear, and to the point. Respond in markdown.\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ebdb34b0-85bd-4e36-933a-20c3c42e833b", + "metadata": {}, + "outputs": [], + "source": [ + "# The job posting and the CV are required to define the user prompt\n", + "# The user will input the job posting as text in a box here\n", + "# The user will upload the CV in PDF format, from which the text will be extracted\n", + "\n", + "# You might need to install PyPDF2 via pip if it's not already installed\n", + "# !pip install PyPDF2\n", + "\n", + "# Create widgets - to create a box for the job posting text\n", + "job_posting_area = Textarea(\n", + " placeholder='Paste the job posting text here...',\n", + " description='Job Posting:',\n", + " disabled=False,\n", + " layout={'width': '800px', 'height': '300px'}\n", + ")\n", + "\n", + "# Define file upload for CV\n", + "cv_upload = FileUpload(\n", + " accept='.pdf', # Only accept PDF files\n", + " multiple=False, # Only allow single file selection\n", + " description='Upload CV (PDF)'\n", + ")\n", + "\n", + "status = HTML(value=\"Status: Waiting for inputs...\")\n", + "\n", + "# Create Submit Buttons\n", + "submit_cv_button = Button(description='Submit CV', button_style='success')\n", + "submit_job_posting_button = Button(description='Submit Job Posting', button_style='success')\n", + "\n", + "# Initialize variables to store the data\n", + "# This dictionary will hold the text for both the job posting and the CV\n", + "# It will be used to define the user_prompt\n", + "for_user_prompt = {\n", + " 'job_posting': '',\n", + " 'cv_text': ''\n", + "}\n", + "\n", + "# Functions\n", + "def submit_cv_action(change):\n", + "\n", + " if not for_user_prompt['cv_text']:\n", + " status.value = \"Status: Please upload a CV before submitting.\"\n", + " \n", + " if cv_upload.value:\n", + " # Get the uploaded file\n", + " uploaded_file = cv_upload.value[0]\n", + " content = io.BytesIO(uploaded_file['content'])\n", + " \n", + " try:\n", + " pdf_reader = PyPDF2.PdfReader(content) \n", + " cv_text = \"\"\n", + " for page in pdf_reader.pages: \n", + " cv_text += page.extract_text() \n", + " \n", + " # Store CV text in for_user_prompt\n", + " for_user_prompt['cv_text'] = cv_text\n", + " status.value = \"Status: CV uploaded and processed successfully!\"\n", + " except Exception as e:\n", + " status.value = f\"Status: Error processing PDF: {str(e)}\"\n", + "\n", + " time.sleep(0.5) # Short pause between upload and submit messages to display both\n", + " \n", + " if for_user_prompt['cv_text']:\n", + " #print(\"CV Submitted:\")\n", + " #print(for_user_prompt['cv_text'])\n", + " status.value = \"Status: CV submitted successfully!\"\n", + " \n", + "def submit_job_posting_action(b):\n", + " for_user_prompt['job_posting'] = job_posting_area.value\n", + " if for_user_prompt['job_posting']:\n", + " #print(\"Job Posting Submitted:\")\n", + " #print(for_user_prompt['job_posting'])\n", + " status.value = \"Status: Job posting submitted successfully!\"\n", + " else:\n", + " status.value = \"Status: Please enter a job posting before submitting.\"\n", + "\n", + "# Attach actions to buttons\n", + "submit_cv_button.on_click(submit_cv_action)\n", + "submit_job_posting_button.on_click(submit_job_posting_action)\n", + "\n", + "# Layout\n", + "job_posting_box = VBox([job_posting_area, submit_job_posting_button])\n", + "cv_buttons = VBox([submit_cv_button])\n", + "\n", + "# Display all widgets\n", + "display(VBox([\n", + " HTML(value=\"

Input Job Posting and CV

\"),\n", + " job_posting_box, \n", + " cv_upload,\n", + " cv_buttons,\n", + " status\n", + "]))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "364e42a6-0910-4c7c-8c3c-2ca7d2891cb6", + "metadata": {}, + "outputs": [], + "source": [ + "# Now define user_prompt using for_user_prompt dictionary\n", + "# Clearly label each input to differentiate the job posting and CV\n", + "# The model can parse and analyze each section based on these labels\n", + "user_prompt = f\"\"\"\n", + "Job Posting: \n", + "{for_user_prompt['job_posting']}\n", + "\n", + "CV: \n", + "{for_user_prompt['cv_text']}\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "id": "3b51dda0-9a0c-48f4-8ec8-dae32c29da24", + "metadata": {}, + "source": [ + "## Messages\n", + "\n", + "The API from OpenAI expects to receive messages in a particular structure.\n", + "Many of the other APIs share this structure:\n", + "\n", + "```\n", + "[\n", + " {\"role\": \"system\", \"content\": \"system message goes here\"},\n", + " {\"role\": \"user\", \"content\": \"user message goes here\"}\n", + "]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3262c0b9-d3de-4e4f-b535-a25c0aed5783", + "metadata": {}, + "outputs": [], + "source": [ + "# Define messages with system_prompt and user_prompt\n", + "def messages_for(system_prompt_input, user_prompt_input):\n", + " return [\n", + " {\"role\": \"system\", \"content\": system_prompt_input},\n", + " {\"role\": \"user\", \"content\": user_prompt_input}\n", + " ]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2409ac13-0b39-4227-b4d4-b4c0ff009fd7", + "metadata": {}, + "outputs": [], + "source": [ + "# And now: call the OpenAI API. \n", + "response = openai.chat.completions.create(\n", + " model = \"gpt-4o-mini\",\n", + " messages = messages_for(system_prompt, user_prompt)\n", + ")\n", + "\n", + "# Response is provided in Markdown and displayed accordingly\n", + "display(Markdown(response.choices[0].message.content))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "86ab71cf-bd7e-45f7-9536-0486f349bfbe", + "metadata": {}, + "outputs": [], + "source": [ + "## If you would like to save the response content as a Markdown file, uncomment the following lines\n", + "#with open('yourfile.md', 'w') as file:\n", + "# file.write(response.choices[0].message.content)\n", + "\n", + "## You can then run the line below to create output.html which you can open on your browser\n", + "#!pandoc yourfile.md -o output.html" + ] + } + ], + "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": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}