What is SmartResume?
SmartResume is an open-source intelligent résumé parsing tool developed by Alibaba. It converts resumes in PDF, image, Word, and other formats into structured data—such as name, education, and work experience—using OCR text extraction, PDF metadata parsing, layout detection, and LLM-based structured processing. The tool uses YOLOv10 for layout detection and a fine-tuned Qwen3-0.6B model for content structuring. It supports both API access and local model deployment, enabling résumé parsing within seconds. SmartResume is widely used in enterprise recruitment, job platforms, campus hiring, and headhunting services, significantly improving HR efficiency.
Key Features
Multi-format Résumé Parsing:
Supports parsing of common résumé formats, including PDF, images, Word, Excel, and more.
OCR & PDF Metadata Extraction:
Combines OCR technology with PDF metadata parsing to extract clean text from documents.
Layout Detection & Reading Order Reconstruction:
Uses the YOLOv10 model to detect résumé layout and identify titles, paragraphs, tables, and other components, then reconstructs the logical reading order.
LLM-powered Structured Processing:
Uses a fine-tuned Qwen3-0.6B model to convert text into structured JSON and extract key fields such as name, phone number, email, and work experience.
Local Model Deployment:
Supports local deployment to reduce reliance on external APIs and ensure data privacy.
API & System Integration:
Provides Python APIs and command-line tools for seamless integration with recruitment systems, enabling automated résumé processing.
How to Use SmartResume
Environment Setup:
Ensure your system meets the minimum requirements (Python 3.9+, ≥8GB RAM, ≥10GB storage; optional CUDA 11.0+ for GPU acceleration).
Clone the Repository:
Use Git to clone the SmartResume project from:
https://github.com/alibaba/SmartResume
Create Environment:
Use Conda to create and activate a Python environment.
Install Dependencies:
Run the setup commands to install all required packages.
Configure Settings:
Copy and edit the configuration template, adding any necessary API keys or custom settings.
Start Parsing:
Use the CLI or Python API to parse résumé files, specifying file paths and target fields.
Local Model Deployment (Optional):
Download the model files and launch the local model service if you prefer offline processing.
SmartResume Project Link
GitHub repository: https://hf-mirror.com/Alibaba-EI/SmartResume
Application Scenarios
Enterprise Recruitment Systems:
Automatically parse incoming résumés, extract key information, and populate HR management systems.
Job Platforms:
Process large volumes of résumés quickly for tagging, ranking, and candidate-job matching.
Campus Recruitment:
Support batch import of student résumés and efficiently match candidates to job openings.
Headhunting Agencies:
Enable structured candidate data management, improving precision in talent matching and recommendations.
HR SaaS Products:
Provide intelligent résumé-entry capabilities via API, making it easy to integrate into HR SaaS platforms.
