In this article, we will be talking about how to use the data extraction part in the application. Let's start!
If you already signed up, log in to your account. In the profile section, you will see the automation button.
Click on the ‘choose file’ area, select your file from your file manager, and click on ‘upload’.
Choose your extraction method. If your PDF doesn't have clear tables, AI OCR is recommended. For large catalogs with clear tables, Classic Extraction is recommended.
Choose your raw text extraction method. AI text extraction takes longer but is better for scanned documents like IDs or invoices.
Choose the complexity level of your document. Select mid or high complexity for PDFs with complex tables, and low complexity for simple tables for faster results.
If you want your data in a specific format, create a dictionary and type your expected format. You can also use or edit the premade formats by navigating to the formats and requests section, choosing your preferred format, and downloading it. Select "I will provide a specific format" and upload your downloaded format.
If your PDF contains tables but you don't have a table format, select "extract table structure" for better alignment with your PDF. If you have a prepared table format, upload it by clicking "I will provide table".
If there is no specific format or no tables inside your PDF, simply select "there is no table inside".
Initiate the extraction process and wait until you receive the results or an error. Once you see the preview of your data, download it as JSON or convert it to an Excel file by clicking "convert to Excel".