CV Analyzer 📄✨

A modern, AI-powered CV analysis tool with an intuitive Streamlit interface. Extract structured data from resumes and analyze candidate fit against job descriptions using advanced AI models.

🌟 Features

1. CV Data Extraction 📊

• Upload CVs in multiple formats (PDF, Word, Text)
• Extract structured information:
  • Personal details (name, email, phone, address)
  • Education history
  • Work experience
  • Skills and competencies
  • Projects and achievements
• Export extracted data as JSON
• Beautiful, organized display of extracted information

2. CV-Job Fit Analysis 🎯

• Compare CVs against job descriptions
• AI-powered matching and scoring (0-10 scale)
• Detailed fit assessment with reasons
• Personalized recommendations for improvement
• Multiple input methods for CVs
• Export analysis reports

🚀 Quick Start

Prerequisites

• Python 3.12+
• UV package manager
• AI Provider API keys (OpenAI or AWS Bedrock)

Installation

1. Clone the repository

   git clone https://github.com/dvarte-dev/cv_analyzer.git
   cd cv_analyzer

2. Install dependencies

   # Install UV
   curl -LsSf https://astral.sh/uv/install.sh | sh
   
   # Instal Project Libs
   uv sync

3. Set up environment variables

   For OpenAI:

   export OPENAI_API_KEY="your-openai-api-key"

   For AWS Bedrock:

   export AWS_ACCESS_KEY_ID="your-access-key"
   export AWS_SECRET_ACCESS_KEY="your-secret-key"
   export AWS_DEFAULT_REGION="us-east-1"

Running the Application

Option 1: Using the launcher script (Recommended)

python run_app.py

Option 2: Direct Streamlit command

streamlit run app/interface.py

Option 3: Using main.py

python main.py

The application will open in your browser at http://localhost:8501

🎨 User Interface

Main Dashboard

• Modern Design: Clean, professional interface with gradient styling
• Responsive Layout: Optimized for desktop and tablet viewing
• Intuitive Navigation: Clear tabs for different functionalities

Configuration Sidebar

• AI Provider Selection: Choose between OpenAI and AWS Bedrock
• Model Selection: Pick from available models for each provider
• Real-time Configuration: Changes apply immediately

📋 How to Use

Extracting CV Data

1. Navigate to the "📄 Extract CV Data" tab
2. Upload your CV file (PDF, Word, or Text format)
3. Wait for AI processing (usually 10-30 seconds)
4. View the extracted structured data
5. Download results as JSON or copy to clipboard

Analyzing CV Fit

1. Go to the "🎯 Analyze CV Fit" tab
2. Provide a CV using one of three methods:
   • Upload a new file
   • Use previously extracted CV
   • Paste CV text directly
3. Enter the job description in the text area
4. Click "🚀 Analyze CV Fit"
5. Review the detailed analysis results:
   • Match score (0-10)
   • Fit assessment (Good/Poor)
   • Overall recommendation
   • Detailed reasons and recommendations
6. Download the analysis report

🤖 AI Models Supported

OpenAI Models

• gpt-4o
• gpt-4.1

AWS Bedrock Models

• claude-4-sonnet (Latest Claude)
• claude-4-opus (Best responses)

📁 Project Structure

cv_analyzer/
├── app/
│   ├── agents/
│   │   ├── cv_analyzer/      # CV analysis agent
│   │   └── data_extractor/   # Data extraction agent
│   ├── interface.py          # Streamlit UI (Main Interface)
│   ├── orchestrator.py       # Coordinates agents
│   └── document_parser.py    # File parsing utilities
├── main.py                   # Application entry point
├── run_app.py               # Streamlit launcher script
└── README.md                # This file

🔧 Technical Details

Architecture

• Frontend: Streamlit with custom CSS styling
• Backend: Pydantic AI agents with structured outputs
• Document Processing: Docling for multi-format support
• AI Integration: Support for multiple providers and models

Data Models

• CVData: Structured schema for extracted CV information
• Response: Analysis results with scoring and recommendations
• Pydantic Validation: Ensures data quality and type safety

🎯 Use Cases

For Recruiters

• Quickly extract key information from candidate CVs
• Batch process multiple resumes
• Standardize CV data for database storage
• Assess candidate-job fit at scale

For HR Professionals

• Streamline initial candidate screening
• Generate consistent evaluation reports
• Identify skill gaps and training needs
• Maintain objective hiring criteria

For Job Seekers

• Understand how well your CV matches job requirements
• Get specific recommendations for improvement
• Optimize CV content for better job matching
• Track CV performance across different roles

🔒 Security & Privacy

• Local Processing: All CV analysis happens locally or through your API keys
• No Data Storage: CVs are not permanently stored by the application
• API Security: Your API keys remain in your environment
• Session Management: Data is cleared when you close the browser

📈 Performance

• Fast Processing: Most CVs processed in under 30 seconds
• Scalable: Handles various document sizes and formats
• Efficient: Optimized API calls and caching
• Responsive: Real-time UI updates and progress indicators

🐛 Troubleshooting

Common Issues

"Failed to initialize AI models"

• Check your API keys are set correctly
• Verify internet connection
• Ensure sufficient API credits/permissions

"Error processing CV"

• Try a different file format
• Check if the file is corrupted
• Ensure the file contains readable text

"Module not found errors"

• Run uv sync to install dependencies
• Check Python version (3.12+ required)

Getting Help

• Check the console output for detailed error messages
• Verify environment variables are set correctly
• Ensure all dependencies are installed

🚧 Development

To contribute or modify the application:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

📄 License

This project is licensed under the terms specified in the LICENSE file.

---

CV Analyzer - Making CV analysis intelligent, fast, and beautiful! 🎉