CareerIQ - AI-Powered Career Assistant 🚀

Team Members:

• Rahul Doshi
• Nihar Patel
• Shailja Maheshwari

Event: Quackathon (Hackathon)

Video Demo: Watch Here

🌟 Overview

Navigating career growth can be overwhelming, especially with ever-changing job markets, evolving skill demands, and varying compensation trends. CareerIQ is a data-driven AI assistant that empowers users to make informed career decisions, explore opportunities, and visualize potential career paths with ease.

✨ Features

• Compensation Trend Analysis: Get insights based on industry and role
• AI-Powered Career Advice: Data-driven simulations of various career paths
• Interactive Visualizations: Dynamic charts to explore opportunities
• Career Q&A: Get answers to career-impacting questions with AI analysis
• Privacy-Focused: Secure handling of sensitive career-related data

Architecture

🛠️ Tech Stack

Frontend:

• Streamlit (Interactive UI)

Backend:

• Python
• OpenAI (GPT-4)
• LangChain
• Presidio (PII detection)

Data Visualization:

• Plotly

🚀 Getting Started

Prerequisites

• Python 3.8+
• pip package manager

Installation

1. Clone the repository

   git clone https://github.com/Nihar-Patel-371/stevenshack25

2. Set up virtual environment

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies

   pip install -r requirements.txt

4. Run the application

   streamlit run streamlit_ui.py

Challanges & Solutions

• Real-time Data Processing: Optimized backend to handle large-scale career data efficiently
• Reliable AI Insights: Fine-tuned prompts and implemented validation layers for actionable advice
• User Experience: Designed intuitive workflows for seamless career exploration
• Data Privacy: Implemented PII detection using NLP and Presidio

Accomplishments

• Built a functional AI career assistant within hackathon timeframe
• Created engaging, interactive data visualizations
• Integrated real-world job market trends for relevant insights
• Developed career progression simulation tool
• Implemented PII detection for security

What we learned

• Effective integration of LLMs with RAG (Retrieval-Augmented Generation)
• PII identification using NLP techniques
• Building responsive UIs with Streamlit
• Processing and visualizing complex career data

🤝 Contributing

We welcome contributions! Please fork the repository and create a pull request with your improvements.