SmartResume - Alibaba's open-source intelligent resume parsing tool

What is SmartResume?

SmartResume is an open-source intelligent resume parsing tool from Alibaba. Through OCR text extraction, PDF metadata parsing, layout detection, and LLM intelligent structuring, SmartResume automatically converts resumes in PDF, image, and Word formats into structured data such as name, education, and work experience. The tool uses YOLOv10 for layout detection and a finely tuned version of Qwen3-0.6B for content structuring. It supports API and local model deployment, completing parsing in seconds. Widely used in corporate recruitment, recruitment platforms, campus recruitment, and headhunting agencies, it significantly improves HR efficiency.

SmartResume's main functions

• Multi-format resume analysisSupports resume parsing in common formats such as PDF, image, Word, and Excel.
• OCR and PDF metadata extractionIt combines OCR technology and PDF metadata parsing to extract plain text content from documents.
• Page layout inspection and reading order reconstructionThe YOLOv10 model was used to detect the resume layout, identify areas such as headings, paragraphs, and tables, and reconstruct the logical reading order.
• LLM Intelligent Structured ProcessingBased on a finely tuned version of the Qwen3-0.6B model, the text content is converted into a structured JSON format, and key fields (such as name, phone number, email, work experience, etc.) are extracted.
• Local model deploymentIt supports local model deployment, reduces reliance on external APIs, and ensures data privacy.
• API calls and integrationIt provides a Python API and command-line interface for easy integration with recruitment systems, enabling automated resume processing.

How to use SmartResume

• Environmental preparationEnsure your device meets the minimum requirements, such as Python 3.9 or later, 8GB or more of memory, and 10GB or more of storage space (CUDA 11.0 or later is optional for GPU acceleration).
• Cloning repositoryClone the SmartResume project (https://github.com/alibaba/SmartResume) to your local machine using Git.
• Creating an environmentUse Conda to create a Python environment and activate it.
• Install dependenciesRun the command to install the project's required dependencies.
• configuration fileCopy the configuration file template and modify it as needed, adding necessary API keys and other information.
• Startup analysisThe parsing function can be invoked via the command-line interface (CLI) or Python API, specifying the resume file path and the types of fields to be extracted.
• Local model deployment(Optional): If you need to deploy the model locally, download the model file and start the local model service to reduce your reliance on external APIs.

SmartResume's project address

• GitHub repositoryhttps://hf-mirror.com/Alibaba-EI/SmartResume

Application scenarios of SmartResume

• Enterprise Recruitment SystemIt automatically parses candidate resumes, extracts key information, and directly populates it into the company's human resource management system.
• Recruitment platformIt can quickly tag and filter massive amounts of resumes, helping recruiters find candidates who meet the job requirements.
• Campus RecruitmentIt supports batch import of student resumes, efficiently matching job requirements and filtering out qualified candidates.
• Headhunting agenciesIt enables structured management of candidate data, achieving accurate matching and recommendations, and improving service quality.
• HR SaaS productsSmartResume offers intelligent resume entry functionality, supports API calls, and can be easily integrated into HR SaaS products.