Resume Parser with OpenAI

A production-ready resume parser built with Go and OpenAI that extracts structured data from PDF, DOCX, and TXT files. Features a modern web interface with drag-and-drop upload and real-time parsing results.

Features

• Multiple File Formats: Supports PDF, DOCX, and TXT files
• Advanced PDF Processing: Uses MuPDF (via go-fitz) for superior text extraction
• OpenAI Integration: Leverages GPT-3.5-turbo for intelligent parsing
• Multiple Prompt Types: Basic, detailed, and skills-focused parsing with UI selection
• Interactive Frontend: Modern Alpine.js UI with drag-and-drop upload and real-time results
• Comprehensive Logging: Detailed logging with structured output
• Production Ready: Docker containerization with Go backend
• Security Features: Input validation, secure file handling, environment variable configuration
• Responsive Design: Mobile-friendly interface with modern styling and improved touch targets

Prerequisites

• Go 1.21 or higher
• OpenAI API key
• Docker (optional, for containerized deployment)

Local Development Setup

1. Clone the Repository

git clone <repository-url>
cd resume-parser

2. Backend Setup

cd backend
go mod tidy

3. Environment Configuration

Create a .env file in the backend directory:

OPENAI_API_KEY=your_openai_api_key_here
GIN_MODE=debug

4. Run the Backend

cd backend
go run main.go

The server will start on http://localhost:8080

5. Test the API

# Health check
curl http://localhost:8080/health

# Parse a resume
curl -X POST -F "file=@resume.pdf" "http://localhost:8080/api/parse-resume?promptType=detailed"

6. Frontend Development

For local development, you can serve the frontend with:

cd frontend
python -m http.server 3000

Then visit http://localhost:3000 and update the API calls to point to http://localhost:8080

Docker Deployment (Recommended)

Quick Start with Docker Compose

1. Set your OpenAI API key:

export OPENAI_API_KEY=your_openai_api_key_here

2. Run the application:

docker-compose up --build

3. Access the application:

• Frontend: http://localhost:3000
• API: http://localhost:8080/api/
• Health Check: http://localhost:8080/health

Using Docker Directly

docker build -t resume-parser .
docker run -p 8080:8080 -e OPENAI_API_KEY=your_key resume-parser

API Endpoints

Health Check

GET /health

Parse Resume

POST /api/parse-resume?promptType={type}

Parameters:

• file: Resume file (PDF, DOCX, or TXT)
• promptType: basic, detailed, or skills-focused

Response:

{
  "filename": "resume.pdf",
  "filetype": ".pdf",
  "text": "extracted text...",
  "parsed": {
    "name": "John Doe",
    "email": "john.doe@example.com",
    "phone": "(555) 123-4567",
    "skills": ["Python", "JavaScript", "React"],
    "experience": [...],
    "education": [...],
    "certifications": [...]
  }
}

Prompt Types

The frontend provides an interactive prompt type selector with the following options:

Basic

Essential information extraction

• Name, email, phone
• Skills list
• Education history
• Work experience

Detailed

Comprehensive extraction with additional fields

• All basic fields
• Detailed job descriptions
• Education details (school, degree, year)
• Certifications
• Languages
• Extended formatting

Skills-Focused

Specialized skill categorization

• Technical skills (programming, tools, frameworks)
• Soft skills (leadership, communication)
• Categorized skill sets
• Skills-optimized parsing

File Processing

Supported Formats

• PDF: Processed using MuPDF (go-fitz) for accurate text extraction
• DOCX: Standard library ZIP-based extraction with XML parsing
• TXT: Direct text processing

File Size Limits

• Maximum file size: 50MB
• Supported formats: PDF, DOCX, TXT

Logging

The application provides comprehensive logging:

• Startup: Configuration and server status
• Request Processing: File details and processing steps
• PDF Extraction: Page-by-page processing with MuPDF
• OpenAI Integration: API calls, timing, and usage statistics
• Error Handling: Detailed error context and debugging info

Security Features

• Input validation and sanitization
• Secure file handling with temporary files
• Environment variable configuration
• Health checks and monitoring
• File type validation

Performance Optimizations

• Efficient PDF Processing: MuPDF for fast, accurate text extraction
• Streaming File Handling: Memory-efficient file processing
• Connection Pooling: Optimized HTTP client for OpenAI API
• Concurrent Processing: Designed for high throughput

Monitoring

• Health check endpoint at /health
• Structured logging with logrus
• Request timing and metrics
• Error tracking and reporting

Error Handling

• Graceful degradation for unsupported files
• Detailed error messages for debugging
• Fallback mechanisms for PDF processing
• Timeout handling for OpenAI API calls
• Safe null handling in frontend expressions

Frontend Features

• Modern UI: Clean, professional interface with improved touch targets
• Drag-and-Drop Upload: Intuitive file upload with visual feedback
• Real-time Processing: Live status updates during parsing
• Responsive Design: Mobile-optimized with larger touch targets
• Error Handling: Comprehensive error display and recovery
• Results Display: Structured presentation of parsed data
• Raw Text View: Collapsible section showing extracted text

Contributing

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

License

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

Troubleshooting

Common Issues

1. PDF Processing Errors: Ensure MuPDF libraries are installed
2. OpenAI API Errors: Check API key and rate limits
3. File Upload Errors: Verify file format and size limits
4. Docker Build Issues: Ensure all dependencies are available
5. Frontend Errors: Check browser console for Alpine.js expression errors

Environment Setup

• Ensure OpenAI API key is properly set in .env file
• Verify Go version is 1.21 or higher
• Check Docker installation for containerized deployment
• Ensure proper file permissions for uploads