Analogous to /wiki/spaces/SD/pages/353140836, the following custom single page ingestion service enables the use of the GA version 2023-07-31 of Microsoft’s Document Intelligence layout service, formerly called Form Recognizer.
Key capabilities:
Leading document ingestion service
Extracts tabular data
Parses multiple column layouts
Enhances search results for complex documents
Can be deployed in Switzerland
Ingestion Config
To use this custom PDF page processing, the ingestion config of the content needs to be adjusted. This ingestion config can be set either on the scope level or on the content directly. This is an example curl for that:
...