I will build a python ocr tool to extract data from invoices, PDF

I
immatomaselli
I
immatomaselli
Imma T
build a python ocr tool to extract data from invoices, PDF
Full Screen
build a python ocr tool to extract data from invoices, PDF
Full Screen
Full Screen
build a python ocr tool to extract data from invoices, PDFbuild a python ocr tool to extract data from invoices, PDFbuild a python ocr tool to extract data from invoices, PDF

About this gig

Are you manually re-typing data from invoices, delivery notes, or 

scanned PDFs into Excel or your accounting system? I'll automate it 

completely.


I build Python tools that extract structured data from any document 

using Google Gemini Vision AI no templates, no fixed formats, no 

manual setup.


WHAT YOU GET:

Automatic detection of document type (invoice, DDT, receipt...)

Full field extraction: vendor, client, VAT, line items, totals

Export to JSON and/or Excel ready for ERP or accounting import

Works on scanned PDFs, digital PDFs, JPG, PNG

Clean Streamlit web interface (no coding needed to use it)

Source code included


HOW IT WORKS:

Upload your PDF AI reads and extracts all fields Download JSON + Excel


Built with: Python · Google Gemini 2.5 Flash Vision · Streamlit · PyMuPDF


See my open-source portfolio:

github.com/Imma91/document-ocr-extractor

  • Application Type

    • Desktop Application

  • Desktop Frameworks

    • Other

  • AI Type

    • Lifestyle
    • Productivity Tools

  • Programming Language

    • Python
    • PyTorch

  • Web Frameworks

    • Other

  • No & Low-Code Builders

    • Other

Get to know Imma T

Imma T

AI Document Automation Developer OCR and PDF Extraction

  • FromItaly
  • Member sinceMay 2018

  • Languages

    English, Italian
I build Python tools that automate document-heavy workflows using AI Vision — extracting structured data from invoices, delivery notes, scanned PDFs, and tables automatically. What I deliver: → OCR extraction from invoices, DDTs, and mixed document batches → Automatic table detection and export to Excel/CSV → Multi-page PDF classification and splitting by document type → Clean JSON/Excel output ready for ERP or accounting systems Tech: Python · Google Gemini Vision · Streamlit · PyMuPDF · pandas All my tools are open source and testable on GitHub before you order.

My Portfolio

Related tags