DEV Community

César Freitas
César Freitas

Posted on

Extract invoice and receipt data to JSON with one API call

#api #python #pdf #rag

Extracting invoice and receipt data from physical documents can be a daunting task for developers and indie makers alike. With the rise of digital payments and online transactions, it's becoming increasingly important to automate this process, but the complexity of extracting relevant data from scanned or digital PDFs makes it a challenging problem.

This is where the Document Intelligence API comes in – an innovative solution that leverages cutting-edge Optical Character Recognition (OCR) technology and natural language processing (NLP) capabilities to transform any digital or scanned PDF into clean, LLM/RAG-ready Markdown text. This not only simplifies data extraction but also ensures the accuracy of the extracted information.

With the Document Intelligence API, you can extract invoice and receipt data from PDFs in a single API call. No longer do you need to manually parse through pages of handwritten notes or scanned receipts, searching for specific keywords like "invoice number" or "date paid." The API's built-in OCR capabilities handle this tedious task for you, ensuring that the extracted data is accurate and reliable.

So, what does a typical request/response look like? When you send a PDF to the Document Intelligence API, it returns a JSON response containing the extracted invoice and receipt data. This includes information such as:

  • Invoice number
  • Date of issue or payment
  • Total amount due
  • Payment method
  • Product descriptions

The response also includes the extracted text in Markdown format, making it easy to integrate into your application.

Here's a brief overview of what you can expect from the API:

  • Request: You send a PDF file containing the invoice or receipt data.
  • Response: A JSON object containing the extracted invoice and receipt data, as well as the original Markdown text.
  • Data: The JSON response includes information such as invoice number, date, total amount due, payment method, and product descriptions.

If you're interested in trying out the Document Intelligence API for yourself, I recommend checking out RapidAPI's free tier. With their free plan, you can send a limited number of requests per month without having to pay any fees. This is an excellent opportunity to test the API, extract some invoice data, and see firsthand how it can simplify your development process.

By leveraging the Document Intelligence API, you can streamline your workflow, reduce manual errors, and focus on more complex tasks. Don't let the complexity of extracting invoice and receipt data hold you back – try out the API today and see the difference it can make for yourself.

Quick example 

curl -X POST 'https://document-intelligence3.p.rapidapi.com/v1/pdf-to-markdown' \
  -H 'X-RapidAPI-Key: YOUR_RAPIDAPI_KEY' \
  -H 'X-RapidAPI-Host: document-intelligence3.p.rapidapi.com' \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://example.com/file.pdf"}'
Enter fullscreen mode Exit fullscreen mode

Try it: the Document Intelligence API is live on RapidAPI with a free tier — get your key here.

Top comments (0)