Upload the PDF of an invoice. Check if the PDF contains a clear text and an XML file compliant with a normalized Factur-X schema. Validate that the PDF is a PDF/A-3b. If the PDF contains photocopies, recover the text of the invoice by OCR. Analyze the conformity of an invoice with regulatory texts. Obtain a report on all the mandatory information present or not in an invoice. Generate the XML file factur-x.xml of an invoice. Convert the PDF and the XML into a PDF/A-3b of an invoice normaized EN 16931.

Factur-X is a file format suitable for exchanging invoices for all types of organizations. It consists of an image file (PDF) and a structured data file (XML). Factur-X complies with the European Semantic Standard EN 16931, published by the European Commission on October 16, 2017.

The PDF/A is an ISO-standardized version of the PDF format specialized for use in the archiving and preservation of electronic documents.

OpenAI is a leading research organization focused on advancing safe and beneficial artificial general intelligence.

Tesseract is an open-source optical character recognition engine supported by Google.

The veraPDF consortium, led by the Open Preservation Foundation and the PDF Association, was created in response to the EU Commission's PREFORMA challenge to develop an open-source validator for the PDF/A format.

Ghostscript is a suite of software for processing Postscript and PDF files.

Poppler provides a set of commands for extracting the pages, the text and the images of PDF files.

Uploading the PDF of an invoice in your personal space runs a series of tests.

Click on the document  to retrieve the clear text extracted from the PDF. Click on the document  to retrieve the XML extracted from the PDF. Click on the trash can  to remove the uploaded file and all the intermidiate files from your personal space.

Facture_F20260023-LE_FOURNISSEUR-POUR-LE_CLIENT_EN_16931.pdf • 302,6k •   •   • 

en16931

The verification of the PDF displays an alert if the file doesn't contain a clear text and an XML file named factur-x.xml compliant with the speficified XSD schema and finally if the PDF isn't a PDF/A-3b.

If the PDF doesn't contain a clear text but a photocopy, try the OCR function to read the text of the invoice.

dpi  

Press OCR to read the text of the PDF. For a PDF containing pages with some text or more than one image, select the resolution in dpi of the images generated for the OCR. Check the option to directly extract just the images (photocopies).

The conformity analysis of the invoice includes the complete list of the required information as explained on the site Service Public - Entreprendre with the values ​​extracted from the invoice or a cross ✗ in case of default. Note that the consistency of all amounts is checked.

Press Report to generate a report of the analysis of the invoice. Click on the download button to download the PDF.

Click on the image to read the report.

The analysis of invoices given as an example by the Forum National de la Facture Électronique et des Marchés Publics Électroniques (FNFE-MPE) is particularly demanding.

Adapting the prompt and the reference documents in parameters of the analysis of your invoices by OpenAI and the presentation and the content of the report with your own ODT document are configurable options in your personal space.

All functionalities are available in the interface of your personal space or by program through a simple REST API. See the User's Guide.

All communications are encrypted.

The files you upload or download are inaccessible to others.