darwin403 / artist-cv-parser

A web application that identifies all Artist's Exhibition Titles from a given CV. The text detection is handled by AWS Textract and title detection is handled by AWS Comprehend.

Artbiogs - Artist CV Parser

A web application that uses AI/ML to extract all Artist's Exhibition details from a CV.

Deploy

Development

You require python3, google-chrome and wkhtmltopdf installed. First clone the repository and change directory to the project folder. Then create a virtual environment:

python3 -m virtualenv .venv
source .venv/bin/activate

Now, run the following:

python setup.py develop

This installs all the necessary dependencies to run the python project. Now, lets launch the web application by running:

python web/app.py

You can now view the application at http://localhost:5000

Technologies

Web Stack:

• Python - Stack core
• Flask + SocketIO - Web Server
• Bulma - CSS Framework
• Selenium - Remote Webpage to PDF conversion
• wkhtmltopdf - HTML to PDF generation.

AI/ML Cloud Technologies used:

• AWS S3 - File Storage
• AWS Textract - Text extraction
• AWS Comprehend - Exhibition Title