Finn/python-pdf-invoice-extractor

A PDF extractor built for extracting data from invoices

About

This tool extracts structured data uploaded PDF invoices. The frontend handles user file upload which then is sent to the backend with FastAPI, which validats the upload and passes the PDF to Claudes API. Claude extracts the invoice data according to the schema and returns once again, structured data.

PythonPythonPyTorchFastAPI

Highlights

  • FastAPI Backend
  • File upload functionality with validation
  • Claude API that returns data in the structure of the schemas file
  • Front end displays specific data from the invoice