Processes enterprise documents with page-based document handling, language understanding and optional retrieval for higher-accuracy workflows.
Shows how document workflows combine provider-native page processing with downstream model analysis. Standard and High Accuracy designs make additional retrieval, reranking and reasoning steps explicit while preserving document pages as a first-class workload quantity.
The same solution, implemented 2 ways. Choosing one changes the workflow and dependencies described below; it does not calculate anything.
4 operations and 6 activities, in the order they run. Expand an operation to see its activities.
Parse the inbound document into text and structure, then form a compact understanding of it.
Decide what kind of business document this is, which is what tells extraction what to look for.
Pull the fields the document class calls for, then normalize them into the canonical shape.
Produce the structured result and a short explanation of how it was arrived at.
For Standard Processing. An activity that calls a model and a service appears in both groups.
Scenario Economics calculates this solution. There you can choose a compatible model or offering for each activity, set workload assumptions and volume, and change the other inputs Standard Processing supports.