An intelligent candidate screening solution powered by GPT-3.5, Langchain, and Streamlit. This system automates the initial interview process by evaluating candidate responses based on technical knowledge, problem-solving skills, and communication ability.
- Interactive Interview Interface: Streamlit-based UI for seamless candidate response collection
- AI-Powered Evaluation: Leverages GPT-3.5 through Langchain for comprehensive response analysis
- Multi-criteria Assessment: Evaluates candidates on:
- Technical Knowledge
- Problem-solving Skills
- Communication Ability
- Automated Ranking: Generates candidate rankings based on performance metrics
- Real-time Feedback: Instant evaluation results and insights
- Frontend: Streamlit
- AI Engine: GPT-3.5
- Framework: Langchain
- Language: Python 3.8+
Before running the system, ensure you have:
- Python 3.8 or higher installed
- OpenAI API key
- Basic understanding of terminal/command line operations
- Clone the repository:
git clone https://github.com/csoren66/AI-Based-Candidate-Screening-System.git
cd AI-Based-Candidate-Screening-System- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install required dependencies:
pip install -r requirements.txt- Set up your environment variables:
# Create a .env file and add your OpenAI API key
echo "OPENAI_API_KEY=your_api_key_here" > .env- Start the Streamlit application:
streamlit run app.py-
Access the application in your web browser (typically http://localhost:8501)
-
Follow the on-screen instructions to:
- Input candidate responses
- Review evaluation results
- Access candidate rankings
The system evaluates candidates based on the following parameters:
- Understanding of core concepts
- Technical accuracy
- Depth of knowledge
- Analytical thinking
- Solution approach
- Innovation and creativity
- Clarity of expression
- Structure and organization
- Professional language use