Invoice Extraction

We extract the necessary information to process invoices

Let's say we get a lot of invoices as a PDF. But for each invoice, we only want to extract the first and last name of the person that gets billed and the total amount to pay.

file-pdf
31KB

Now let's construct a Shape to extract those fields.

Once the shape is defined, we can call the /extract-document endpoint with it and the invoice PDF in the payload to create this job:

We then process your call. Typically the job completion time lies between 10s and 3 minutes. From our request, we receive the following response:

With urls["get"] we can now query that job. This calls our job endpoint with the correct job_id conveniently already pre-filled. If we call this URL 20s later when the job has finished, we get back the following:

In this response, we see the job status has changed to FINISHED and the result field now contains our requested information.

Last updated