Adobe provides an API to perform all sorts of manipulation on PDF files:

– Split PDF
– Combine PDF
– OCR
– Insert page, delete page, replace page, reorder page
– Content extraction (text content, tables, pictures)

The free tier allows up to 500 PDF operations/month. As it comes directly from Adobe, it often works better than other alternatives.

### What does this workflow do?

The API can be a bit painful to use. To perform a transformation on a PDF, it requires:

1. Authenticate and get a temporal token
2. Register a new asset (file)
3. Upload your PDF to the registered asset
4. Perform a query according to the transformation requested
5. Wait for the query to be processed by Adobe backend
6. Download the result

This workflow is a generic wrapper to perform all these steps for any transformation endpoint. I usually use it from other workflows with an Execute Workflow node. Examples are given in the workflow.

### Example use case

This service is useful for cleaning PDF data for an AI/RAG system. My favorite use case is to extract tables as images and forward the images to an AI for image recognition/description, which is often more accurate than feeding raw tabular data to a LLM.