AI-Powered Job Search Platform

A modern web application that leverages AI and vector search to help users find relevant job postings. Built with SvelteKit, Weaviate, and Ollama.

✨ Features

• AI-Powered Search: Utilizes vector embeddings for semantic job search
• Modern Web Interface: Built with SvelteKit and Tailwind CSS
• Vector Database: Uses Weaviate for efficient similarity search
• Local LLM Integration: Supports local language models via Ollama
• Responsive Design: Works on desktop and mobile devices

🚀 Quick Start

Prerequisites

• Docker and Docker Compose
• Node.js (v18 or later)
• PNPM package manager
• Ollama for local LLM support

Installation

1. Clone the repository

   git clone <repository-url>
   cd jobsearch-ai

2. Set up the backend

   cd data
   docker compose up -d

3. Install Ollama and required models

   ollama pull llama3.2:3b
   ollama pull nomic-embed-text

4. Run the data pipeline

   # In the data directory
   python 1.scrape_jobs.py
   python 2.jobs_fix.py
   python 3.quickstart_check_readiness.py
   python 4.quickstart_create_collection.py
   python 5.quickstart_import.py

5. Set up the frontend

   cd ../app
   pnpm install
   pnpm run dev

6. Open your browser Visit http://localhost:5173 to access the application

🛠️ Project Structure

• /app - Frontend SvelteKit application
• /data - Data processing scripts and Weaviate configuration
  • scrape_jobs.py - Job scraping script
  • jobs_fix.py - Data cleaning and processing
  • quickstart_*.py - Weaviate setup and data import scripts
  • docker-compose.yml - Weaviate container configuration

🤖 Technologies Used

• Frontend: SvelteKit, TypeScript, Tailwind CSS, DaisyUI
• Backend: Weaviate (vector database)
• AI/ML: Ollama with LLaMA 3.2 and Nomic Embed Text models
• Data Processing: Python

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Weaviate for the vector database
• Ollama for local LLM support
• Jobspy for job listing data
• SvelteKit for the web framework