From this article you will learn how to:
How to split PDF into multiple documents
It is often convenient to process multiple documents stored in a single file. Most commonly, you would scan many documents at once in a scanner with an automatic feeder, resulting in a single file containing all of the scanned pages.
Using a special separator page, you can automatically split a file in Rossum. Print the QR code on separate pieces of paper and place them between documents while scanning. When you upload the file to Rossum, the engine will instantly recognize these pages, resulting in multiple document entries in your queue.
If using the special separator page is impossible, you can use the document slicing tool to split the file into multiple documents.
- On the Validation screen, you will see an Edit button on the right side.
- Clicking this button will open a Document editing screen with a list of pages.
- When you move the cursor between two consecutive pages, you will see a “split line”.
- The document will split if you click on it, and an updated list of pages will appear.
- When satisfied with the outcome, click the “tick” button in the upper right corner.
Note: The original document will be removed, and the new documents will appear in the queue. Those documents need to be reprocessed by Rossum AI Engine, which typically takes between 30-60 seconds.
Automatic splitting suggestions
The ability to automatically suggest how to split a larger document into multiple ones is a typical demand when processing invoices in accounts payable workflows. Therefore, we made this possible.
When Rossum detects a batch of documents, you will see a “scissors” icon on the document’s dashboard.
Click on it to open the document editing screen, where you can split, delete, or rotate pages by 90 degrees.
Once Rossum has detected such a document, you should immediately see the suggested splits. The suggested splits can be updated or accepted as if you would typically split the documents without any suggestions. Moreover, if you disagree with the splits, you could disable them by turning off the “Suggested split” visible at the top of the screen.
How to enable splitting suggestions
To enable this functionality, you should:
- Pick a queue.
- Open the queue’s Settings.
- Navigate to the Document section.
- Pick the right option in the “Split batch files” dropdown.
Currently, you can set one of the following options:
- “Do not suggest” -> Detection of batch files and suggestion of possible splits will not be performed.
- “Suggest” -> Will try to detect batch files and recommend splits for newly uploaded files.
Limitations of the automatic split suggestions
This new functionality currently has a few limitations:
- Detecting batch files and suggesting splits can be enabled only on queues with Generic AI Engine. Please contact us at firstname.lastname@example.org if you want us to enable this functionality on queues with Dedicated AI Engine. Read more about the difference between the two engines.
- By default, Rossum’s AI Engine captures data only from the first 32 pages. The same limit applies to the detection of possible splits. If needed, this limit can be extended. Don’t hesitate to contact us at email@example.com if you want to increase this limit.