-
Notifications
You must be signed in to change notification settings - Fork 7
User Guide
Gaurav-Kumar98 edited this page Mar 24, 2025
·
1 revision
This guide will help you use the Resume Analysis tool effectively to process and analyze resumes.
- Place your resume files (PDF or DOCX) in the
Resumes/directory - Run the main script:
python main.py
- Find the processed results in the
Results/directory
The tool supports various command-line arguments for different use cases:
# Process a single resume file
python main.py --resume example.pdf
# Display token usage report for a previously processed resume
python main.py --resume example.pdf --report-only
# Specify a custom directory for token usage logs
python main.py --log-dir ./custom_logs
# Enable verbose logging
python main.py --verbose
# Clean up __pycache__ directories and compiled Python files
python main.py --cleanupThe tool generates structured JSON output for each processed resume:
{
"name": "John Doe",
"contact_number": "+1-123-456-7890",
"email": "john.doe@example.com",
"skills": [
"Python",
"Machine Learning",
"Data Analysis",
"SQL",
"JavaScript"
],
"educations": [
{
"institution": "University of Example",
"start_date": "2015-09",
"end_date": "2019-05",
"location": "Boston, MA",
"degree": "Bachelor of Science in Computer Science"
}
],
"work_experiences": [
{
"company": "Tech Company Inc.",
"start_date": "2019-06",
"end_date": "2023-03",
"location": "San Francisco, CA",
"role": "Software Engineer"
}
],
"YoE": "4 years"
}The system tracks and reports token usage for each processed resume:
{
"resume_file": "John_Doe.pdf",
"processed_at": "20250323_031534",
"token_usage": {
"total_tokens": 7695,
"prompt_tokens": 7410,
"completion_tokens": 285,
"by_extractor": {
"ProfileExtractorPlugin": {
"total_tokens": 1445,
"prompt_tokens": 1423,
"completion_tokens": 22
},
"SkillsExtractorPlugin": {
"total_tokens": 1383,
"prompt_tokens": 1304,
"completion_tokens": 79
},
"EducationExtractorPlugin": {
"total_tokens": 1672,
"prompt_tokens": 1624,
"completion_tokens": 48
},
"ExperienceExtractorPlugin": {
"total_tokens": 1704,
"prompt_tokens": 1586,
"completion_tokens": 118
},
"YoeExtractorPlugin": {
"total_tokens": 1491,
"prompt_tokens": 1473,
"completion_tokens": 18
}
}
}
}To process multiple resumes efficiently:
- Place all resumes in the
Resumes/directory - Run the main script without arguments:
python main.py
- The tool will process all resumes concurrently and generate results in the
Results/directory
To optimize token usage:
- Monitor token usage reports in the
logs/token_usagedirectory - Adjust prompt templates in plugins if needed
- Use the
--report-onlyflag to analyze token usage without reprocessing
The system provides comprehensive logging:
- Main application logs in
resume_analysis.log - Token usage logs in
logs/token_usage/ - Debug logs when
DEBUG=Truein.env
Logs are automatically rotated based on size and retention settings in .env.
-
Resume Format
- Use PDF or DOCX format for best results
- Ensure resumes are properly formatted and readable
- Avoid scanned documents or images
-
Performance
- Process resumes in batches for better efficiency
- Monitor token usage to optimize costs
- Clean up old logs regularly
-
Error Handling
- Check logs for processing errors
- Verify API key validity
- Ensure sufficient disk space
-
Security
- Keep API keys secure
- Regularly rotate API keys
- Don't share processed results containing sensitive information
-
API Errors
- Check API key validity
- Verify internet connection
- Monitor API rate limits
-
Processing Failures
- Check resume file format
- Verify file permissions
- Review error logs
-
Token Usage Issues
- Monitor token usage reports
- Check prompt templates
- Verify API quota
- Check the FAQ & Troubleshooting page
- Review the Examples & Tutorials
- Open an issue on GitHub for bugs or feature requests