Natural language processing
CVLens.
From a resume to structured information. An NLP-powered application that gives unstructured documents a useful shape.
THE OVERVIEW
What’s the idea?
A group-built web application that extracts contact information, education, skills, and work experience from PDF and DOCX resumes.
The problem.
Resume information often arrives in layouts that require repetitive manual data entry.
The approach.
A SpaCy named-entity recognition model processes uploaded resumes. A FastAPI REST API returns structured JSON, and a Next.js frontend presents the extracted details.
INSIDE THE BUILD
Details that matter.
Document ingestion
Upload PDF or DOCX resumes for processing.
Named-entity recognition
Extract contact details, education, skills, and work history with SpaCy. The project included a dataset of over 200 resumes.
Structured responses
A RESTful FastAPI service returns extracted information as JSON.
An approachable interface
The Next.js frontend fetches API results and displays the information in a readable format.
TECHNICAL FLOW / A HIGH-LEVEL VIEW
- 01
PDF / DOCX upload
- 02
FastAPI service
- 03
SpaCy NLP extraction
- 04
JSON & Next.js
KEEP EXPLORING / NEXT PROJECT