How harry3602/resume-builder-using-nlp works
Project Type and Purpose
• Project type: a CLI/open-source tool for automated resume generation.
• Purpose: read candidate data + job description from JSON, extract/match skills with NLP, and produce a .docx resume.
Main Components
a. Input Layer
• JSON File (input.json)
• CLI Invocation (python resume_builder.py)
b. NLP Processing Module
• spaCy Model (en_core_web_sm)
• Text extraction & keyword matching sub-component
c. Resume Generation Module
• Objective Generator
• Section Builders (Education, Experience, Skills, Projects, Certificates)
• python-docx Integration
d. Output Layer
• Generated Word Document (generated_resume.docx)
e. Environment & Dependencies
• Python Runtime (3.8+)
• Virtual Environment (venv)
• External Libraries (spacy, python-docx)
Architectural Patterns & Principles
• Modular design: separate parser, NLP logic, document builder
• Single responsibility: each component has one clear purpose
• Dependency injection: pass parsed data into NLP and builder modules
Detailed Breakdown
Top row:
[ input.json ] —> [ JSON Parser ]
Middle row (left to right):
[ JSON Parser ] —> [ NLP Processing ] —> [ Resume Builder ]
Bottom row:
[ Resume Builder ] —> [ generated_resume.docx ]
Off to the side:
• python-docx library (connects to Resume Builder)