Navigating the job market one prompt at a time .
Aileana is an advanced LLM chatbot that provides deep insights into the job market, helping individuals navigate career paths and keeping professionals updated on market trends. Using state-of-the-art LLMs and Retrieval-Augmented Generation (RAG), Aileana analyzes job postings to identify correlations between jobs, skills, requirements, benefits, experience, and responsibilities.
- 🤖 AI-powered job market analysis
- 📊 Interactive data visualizations
- 💬 Intelligent chatbot with market insights
- 🔍 Advanced search and filtering
- 📈 Real-time market trend analysis
Eleana was nearly 18 years old, facing the critical decision of choosing her career and relevant academic studies.
She had a passion for Biology (or at least thought she did) , but no one in her family or circle was familiar with this field, and the job prospects were uncertain 🤔.
Given my background in the health domain, she asked me if pursuing Biology was a good idea. My response was something like: " If it is your passion, follow it. "
However, this answer was generic and insincere , to be honest. The truth was that I had no idea. This led me to ponder:
- Is it really good advice? Is 'liking' a subject the only criterion for choosing a field of study?
- What are the employment prospects after graduation?
- What related jobs are available, and what other skills are needed to qualify for these jobs?
- What benefits do such jobs usually offer?
As a data nerd 🤓, I realized the job market operates like any other market:
- Supply and demand are key driving forces.
- Higher qualifications/specializations generally lead to higher pay.
Only data can provide answers to these questions, not anecdotal experiences.
Thus, Aileana , this project, was born.
| Category | Technology |
|---|---|
| Frontend |  |
| Backend |  |
| Databases |   |
| Web Scraping |   |
| Data Processing |  |
| DevOps |  |
| Testing |  |
| LLM Frameworks |      |
├── components/ # Reusable UI components
├── pages/ # Streamlit pages
├── static/ # Static assets
├── Home.py # Main application entry
└── requirements.txt # Python dependencies
- Web scraping of job listings
- Translation to English
- Storage in PostgreSQL
- LLM processing for structured data
- Neo4j graph database population
- Vector embeddings creation
- RAG-enhanced user interactions
More information on the data extraction and classification pipeline using LLM AI agents can be found here.
- NACE V2 (Economic Activities)
- ISCED 2011 (Education Levels)
- ISCO-88 (Occupation Classifications)
This project is licensed under the MIT License - see the LICENSE.md file for details.
Made with ❤️ by Dimitris Koutsomichalis