Skip to main content

AI-powered resume screening tool using LLMs and Streamlit

Project description

🧠 AI-Powered Resume Screener

A lightweight resume screening app that uses AI to extract key candidate details from PDFs and evaluates them based on skills. Built with Streamlit, SQLite, and PyMuPDF. Ideal for HR teams, devs, or anyone needing a smart CV filter!


📸 Screenshots

Home Screen Upload resumes and view extracted details

Parsed Resume Table See candidate info and download PDF


🚀 Features

  • 📄 PDF Resume Upload
  • 🧠 LLM-Based Evaluation (GPT or any open-source LLM)
  • 🧑‍💻 Name, Email, Skills Extraction
  • 🗃 Resume Storage with SQLite
  • 📊 Interactive Table View

🛠️ Tech Stack

  • Frontend: Streamlit
  • Backend: Python, PyMuPDF, SQLite
  • AI: OpenAI / GPT-compatible LLMs / Together.ai (pluggable)

🔄 Pluggable LLM Support By default, this project uses GPT for resume evaluation. You can use any open-source LLM model (like Mistral, LLaMA, Gemma, etc.) by simply updating the model name or API in the gpt_evaluator.py file.


⚙️ Getting Started

git clone https://github.com/your-username/ai-resume-screener.git
cd ai-resume-screener
pip install -r requirements.txt
streamlit run app.py

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_resume_screener-0.1.0.tar.gz (6.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_resume_screener-0.1.0-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file ai_resume_screener-0.1.0.tar.gz.

File metadata

  • Download URL: ai_resume_screener-0.1.0.tar.gz
  • Upload date:
  • Size: 6.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for ai_resume_screener-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4b9219a01123178fa5c6c4413513ae1aa2c8bcb2112aaf9d2862c49283fb0315
MD5 2be6240d464498ac1914d0e562a5cb25
BLAKE2b-256 7a4726e18e42fb84e5593e3c78513365d0b3ec091e4b3121305f4e212a63f2c0

See more details on using hashes here.

File details

Details for the file ai_resume_screener-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ai_resume_screener-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 cdbb076ab7368fe900fabc4a4c2f840819f47460ffaa22eb2046e888bca21bac
MD5 eb23bcc3d36d5f6c76c328cd1351c6e5
BLAKE2b-256 9e455388a223c8285752872ddc5a2e639574dfa915aa96e77a8700da45c7c28c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page