AIRA - AI Recruitment Assistant

🎯 AI-powered tools for HR professionals

Overview

AIRA is an intelligent platform designed to streamline recruitment processes and ensure compliance. It combines cutting-edge AI with practical HR tools to make recruitment faster, more accurate, and compliant with regulations.

Key Features

🎯 Talent Recommendation

An AI-powered system that matches candidate profiles with job requirements:

• Intelligent Matching: Uses advanced AI algorithms to match candidates with positions
• Natural Language Processing: Understand job descriptions and candidate skills
• Custom Criteria: Tailor recommendations based on specific requirements
• Visual Results: Clear visualization of candidate matches with supporting data

✅ Compliance Checker

Ensures that employee documentation meets regulatory requirements:

• Document Processing: Extract text from PDF and image-based documents using OCR
• AI-Powered Parsing: Parse unstructured text into structured data using LLMs
• Cross-Document Validation: Compare data across multiple documents to verify consistency
• Truth Value Determination: Find the most authoritative source for each data field

Technical Stack

• Frontend: Streamlit
• Backend: Python
• AI Models: LangGraph, LangChain, Google Gemini AI
• Document Processing: OCR technologies, PDF parsing
• Containerization: Docker

Getting Started

Prerequisites

• Python 3.10.11
• Google API key (for AI features)
• Pinecone API key (for vector database)
• Docker (optional, for containerized deployment)

Quick Start

1. Clone the repository

git clone https://github.com/TenAkihiro/project-assist-employe-agentic-ai.git
cd project-assist-employe-agentic-ai

2. Install dependencies

pip install -r requirements.txt

3. Set up environment variables and fill the .env file

cp .env.example .env
nano .env

4. Run the application

streamlit run app.py

Login Information

Use one of the following credential pairs to log in:

• Username: admin / Password: admin123
• Username: user / Password: user123
• Username: demo / Password: demo123

Project Structure

project-assist-employe-agentic-ai/
├── app.py                    # Main Streamlit application
├── pages/                    # Application pages
│   ├── talent_recommendation.py
│   └── compliance_checker.py
├── features/                 # Core functionality modules
│   ├── compliance_checker/   # Document compliance checking
│   │   ├── config/           # Configuration settings
│   │   ├── core/             # Core processing logic
│   │   ├── prompts/          # AI prompt templates
│   │   ├── schemas/          # Data models and schemas
│   │   └── services/         # Service implementations
│   └── bulk_document/        # Bulk document processing features
│       ├── agentic/          # AI agent implementation
│       ├── chat_models/      # LLM integration and chat models
│       ├── config/           # Configuration settings
│       ├── embeddings/       # Vector embedding services
│       ├── prompts/          # Prompt templates for LLMs
│       ├── schemas/          # Data schemas and validation
│       ├── ui/               # User interface components
│       └── utils/            # Utility functions and helpers
├── assets/                   # Static assets
├── data/                     # Data storage
├── utils/                    # Utility functions
├── .streamlit/               # Streamlit configuration
├── docker-compose.yml        # Docker composition
├── Dockerfile                # Container definition
└── requirements.txt          # Project dependencies

Docker Deployment

You can run this project using Docker:

1. Ensure Docker and Docker Compose are installed on your system

2. Build and start the container:

docker-compose up --build

3. Access the application at http://localhost:8501

4. To stop the application:

docker-compose down

License

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