Resume Classifier

A simple web application that classifies text and markdown files to determine if they are resumes using OpenAI's Responses API with the gpt-5-nano model.

Features

• Upload individual or multiple files (.txt or .md)
• Parallel processing of multiple files for fast classification
• Real-time results display with classification status and response time
• Persistent storage using localStorage
• Clean, modern UI with drag-and-drop support
• Clear button to reset results

Prerequisites

• Node.js (v18 or higher)
• OpenAI API key with access to gpt-5-nano model

Setup

1. Install dependencies:

   npm install

2. Set your OpenAI API key:

   macOS/Linux:

   export OPENAI_API_KEY='your-api-key-here'

   Windows (PowerShell):

   $env:OPENAI_API_KEY='your-api-key-here'

3. Start the server:

   npm start

   For development with auto-reload:

   npm run dev

4. Open your browser: Navigate to http://localhost:3000

Usage

1. Upload Files:

   • Click the upload area or drag and drop files
   • Select one or multiple .txt or .md files
   • Click "Classify Files" button

2. View Results:

   • See classification results in the table
   • Each result shows: filename, classification (Yes/No), duration, and timestamp
   • Results are automatically saved in browser localStorage

3. Clear Results:

   • Click "Clear All" button to remove all results from the table and localStorage

API Configuration

The application uses OpenAI's Responses API with the following configuration:

• Model: gpt-5-nano
• Reasoning Effort: minimal
• Verbosity: low
• Response Format: Structured JSON with schema validation

The classification prompt and response schema are defined directly in server.js.

For detailed API integration documentation, see OPENAI_INTEGRATION.md.

Project Structure

.
├── server.js                   # Express backend server
├── package.json                # Project dependencies
├── OPENAI_INTEGRATION.md       # Detailed OpenAI API documentation
└── public/
    ├── index.html              # Main HTML page
    ├── style.css               # Styles
    └── app.js                  # Frontend JavaScript

Tech Stack

• Backend: Node.js, Express, Multer
• Frontend: Vanilla JavaScript, HTML5, CSS3
• API: OpenAI Responses API
• Storage: Browser localStorage

Notes

• This is a local testing application, not production-ready
• File size limit: 10MB per file
• All processing happens asynchronously for better performance
• Results persist across browser sessions via localStorage
• The app requires an active internet connection to communicate with OpenAI API

Environment Variables

• OPENAI_API_KEY (required): Your OpenAI API key
• PORT (optional): Server port (default: 3000)

Troubleshooting

"OPENAI_API_KEY environment variable is not set"

• Make sure you've set the environment variable before starting the server

"OpenAI API error: 401"

• Check that your API key is valid and has proper permissions

"OpenAI API error: 404"

• Ensure your API key has access to the gpt-5-nano model

License

MIT