Merge pull request #352 from subh273/community-contributions-branch
Added Resume Analyzer and Sample version
This commit is contained in:
Ed Donner
GitHub
@@ -0,0 +1,234 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "4e2a9393-7767-488e-a8bf-27c12dca35bd",
|
||||||
|
"metadata": {},
|
||||||
|
"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",
|
||||||
|
"\n",
|
||||||
|
"# If you get an error running this cell, then please head over to the troubleshooting notebook!"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "7b87cadb-d513-4303-baee-a37b6f938e4d",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Load environment variables in a file called .env\n",
|
||||||
|
"\n",
|
||||||
|
"load_dotenv(override=True)\n",
|
||||||
|
"api_key = os.getenv('OPENAI_API_KEY')\n",
|
||||||
|
"\n",
|
||||||
|
"# Check the key\n",
|
||||||
|
"\n",
|
||||||
|
"if not api_key:\n",
|
||||||
|
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
|
||||||
|
"elif not api_key.startswith(\"sk-proj-\"):\n",
|
||||||
|
" print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
|
||||||
|
"elif api_key.strip() != api_key:\n",
|
||||||
|
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
|
||||||
|
"else:\n",
|
||||||
|
" print(\"API key found and looks good so far!\")\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "019974d9-f3ad-4a8a-b5f9-0a3719aea2d3",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"openai = OpenAI()\n",
|
||||||
|
"\n",
|
||||||
|
"# If this doesn't work, try Kernel menu >> Restart Kernel and Clear Outputs Of All Cells, then run the cells from the top of this notebook down.\n",
|
||||||
|
"# If it STILL doesn't work (horrors!) then please see the Troubleshooting notebook in this folder for full instructions"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "abdb8417-c5dc-44bc-9bee-2e059d162699",
|
||||||
|
"metadata": {},
|
||||||
|
"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 a high profile professional resume analyst and assist users with highlighting gaps in a very formed resume and provide direction to make the resume eye catching to the recruiters \\\n",
|
||||||
|
"and employers.\"\n",
|
||||||
|
"\n",
|
||||||
|
"user_prompt = \"\"\"Analyze the resume details to do the following: \\\n",
|
||||||
|
"1. Assess the resume to highlight areas of improvement. \\ \n",
|
||||||
|
"2. Create a well formed resume.\n",
|
||||||
|
"\n",
|
||||||
|
"Name: Sam Burns\n",
|
||||||
|
"\n",
|
||||||
|
"PROFESSIONAL SUMMARY\n",
|
||||||
|
"Experienced Data and AI Architect with over 10 years of expertise designing scalable data platforms, integrating cloud-native solutions, and deploying AI/ML systems across enterprise environments. Proven track record of aligning data architecture with business strategy, leading cross-functional teams, and delivering high-impact AI-driven insights.\n",
|
||||||
|
"\n",
|
||||||
|
"CORE SKILLS\n",
|
||||||
|
"\n",
|
||||||
|
"Data Architecture: Lakehouse, Data Mesh, Delta Lake, Data Vault\n",
|
||||||
|
"\n",
|
||||||
|
"Cloud Platforms: Azure (Data Factory, Synapse, ML Studio), AWS (S3, Glue, SageMaker), Databricks\n",
|
||||||
|
"\n",
|
||||||
|
"Big Data & Streaming: Spark, Kafka, Hive, Hadoop\n",
|
||||||
|
"\n",
|
||||||
|
"ML/AI Tooling: MLflow, TensorFlow, Scikit-learn, Hugging Face Transformers\n",
|
||||||
|
"\n",
|
||||||
|
"Programming: Python, SQL, PySpark, Scala, Terraform\n",
|
||||||
|
"\n",
|
||||||
|
"DevOps: CI/CD (GitHub Actions, Azure DevOps), Docker, Kubernetes\n",
|
||||||
|
"\n",
|
||||||
|
"Governance: Data Lineage, Cataloging, RBAC, GDPR, Responsible AI\n",
|
||||||
|
"\n",
|
||||||
|
"PROFESSIONAL EXPERIENCE\n",
|
||||||
|
"\n",
|
||||||
|
"Senior Data & AI Architect\n",
|
||||||
|
"ABC Tech Solutions — New York, NY\n",
|
||||||
|
"Jan 2021 – Present\n",
|
||||||
|
"\n",
|
||||||
|
"Designed and implemented a company-wide lakehouse architecture on Databricks, integrating AWS S3, Redshift, and real-time ingestion from Kafka.\n",
|
||||||
|
"\n",
|
||||||
|
"Led architecture for a predictive maintenance platform using sensor data (IoT), Spark streaming, and MLflow-managed experiments.\n",
|
||||||
|
"\n",
|
||||||
|
"Developed enterprise ML governance framework ensuring reproducibility, fairness, and compliance with GDPR.\n",
|
||||||
|
"\n",
|
||||||
|
"Mentored 6 data engineers and ML engineers; led architectural reviews and technical roadmap planning.\n",
|
||||||
|
"\n",
|
||||||
|
"Data Architect / AI Specialist\n",
|
||||||
|
"Global Insights Inc. — Boston, MA\n",
|
||||||
|
"Jun 2017 – Dec 2020\n",
|
||||||
|
"\n",
|
||||||
|
"Modernized legacy data warehouse to Azure Synapse-based analytics platform, reducing ETL latency by 40%.\n",
|
||||||
|
"\n",
|
||||||
|
"Built MLOps pipelines for customer churn prediction models using Azure ML and ADF.\n",
|
||||||
|
"\n",
|
||||||
|
"Collaborated with business units to define semantic layers for self-service analytics in Power BI.\n",
|
||||||
|
"\n",
|
||||||
|
"Data Engineer\n",
|
||||||
|
"NextGen Analytics — Remote\n",
|
||||||
|
"Jul 2013 – May 2017\n",
|
||||||
|
"\n",
|
||||||
|
"Developed ETL pipelines in PySpark to transform raw web traffic into structured analytics dashboards.\n",
|
||||||
|
"\n",
|
||||||
|
"Integrated NLP models into customer support workflows using spaCy and early versions of Hugging Face.\n",
|
||||||
|
"\n",
|
||||||
|
"Contributed to open-source tools for Jupyter-based analytics and data catalog integration.\n",
|
||||||
|
"\n",
|
||||||
|
"EDUCATION\n",
|
||||||
|
"M.S. in Computer Science – Carnegie Mellon University\n",
|
||||||
|
"B.S. in Information Systems – Rutgers University\n",
|
||||||
|
"\n",
|
||||||
|
"CERTIFICATIONS\n",
|
||||||
|
"\n",
|
||||||
|
"Databricks Certified Data Engineer Professional\n",
|
||||||
|
"\n",
|
||||||
|
"Azure Solutions Architect Expert\n",
|
||||||
|
"\n",
|
||||||
|
"AWS Certified Machine Learning – Specialty\n",
|
||||||
|
"\n",
|
||||||
|
"PROJECTS & CONTRIBUTIONS\n",
|
||||||
|
"\n",
|
||||||
|
"llm_engineering (GitHub): Developed and maintained hands-on LLM course materials and community contributions framework.\n",
|
||||||
|
"\n",
|
||||||
|
"Real-time AI PoC: Designed Kafka-Spark pipeline with Azure OpenAI Service for anomaly detection on IoT streams.\n",
|
||||||
|
"\n",
|
||||||
|
"Contributor to Hugging Face Transformers – integration examples for inference pipelines\n",
|
||||||
|
"\"\"\""
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "4e6a8730-c3ad-4243-a045-0acba2b5ebcf",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"messages = [\n",
|
||||||
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
||||||
|
" {\"role\": \"user\", \"content\": user_prompt}\n",
|
||||||
|
"]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "21ed95c5-7001-47de-a36d-1d6673b403ce",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# To give you a preview -- calling OpenAI with system and user messages:\n",
|
||||||
|
"\n",
|
||||||
|
"response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "3d926d59-450e-4609-92ba-2d6f244f1342",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# A function to display this nicely in the Jupyter output, using markdown\n",
|
||||||
|
"\n",
|
||||||
|
"display(Markdown(response.choices[0].message.content))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "eeab24dc-5f90-4570-b542-b0585aca3eb6",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"# Sharing your code\n",
|
||||||
|
"\n",
|
||||||
|
"I'd love it if you share your code afterwards so I can share it with others! You'll notice that some students have already made changes (including a Selenium implementation) which you will find in the community-contributions folder. If you'd like add your changes to that folder, submit a Pull Request with your new versions in that folder and I'll merge your changes.\n",
|
||||||
|
"\n",
|
||||||
|
"If you're not an expert with git (and I am not!) then GPT has given some nice instructions on how to submit a Pull Request. It's a bit of an involved process, but once you've done it once it's pretty clear. As a pro-tip: it's best if you clear the outputs of your Jupyter notebooks (Edit >> Clean outputs of all cells, and then Save) for clean notebooks.\n",
|
||||||
|
"\n",
|
||||||
|
"Here are good instructions courtesy of an AI friend: \n",
|
||||||
|
"https://chatgpt.com/share/677a9cb5-c64c-8012-99e0-e06e88afd293"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "f4484fcf-8b39-4c3f-9674-37970ed71988",
|
||||||
|
"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": "3.11.12"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 5
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user