hxu296/nlp-resume-parser
NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.
Exposes a Flask REST API that converts resume PDFs to structured JSON by leveraging GPT-3's `text-davinci-002` engine, extracting 25+ fields across personal info, education, job experience, and projects. Uses `pdftotext` for PDF-to-text conversion before passing to OpenAI's API, with typical requests consuming 1500-3000 tokens (~$0.03-$0.06 per parse). Processing takes ~15 seconds per resume and supports fine-tuning for improved accuracy beyond the out-of-the-box results.
276 stars. No commits in the last 6 months.
Stars
276
Forks
57
Language
Python
License
—
Category
Last pushed
Jun 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/hxu296/nlp-resume-parser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
techwolf-ai/workrb
WorkRB: Work Research Benchmark
yogeshhk/MiningResume
Text Mining certain fields from a resume
AnasAito/SkillNER
A (smart) rule based NLP module to extract job skills from text
microsoft/SkillsExtractorCognitiveSearch
Azure Search Cognitive Skill to extract technical and business skills from text
mynameisvinn/EmailParser
remove signature blocks from emails