Skip to main content

Document Classifications

Every document in the Foundation4.ai API system must specify a document classification that is a known classification of the Pipeline it belongs to. The classification system within a pipeline is a hierarchical grouping of levels specifying access to that document. For example, we could have a pipeline with the following diagram

In the case above, all documents tagged with a General classification will be used for any query to the pipeline. Queries tagged as Secret 1 will use documents tagged as Secret 1, Classified 1, Classified 2, and General. Top Secret queries will use all the documents in the pipeline.

Search Types​

Foundation4.ai supports two types of classification-based searches:

An exact classification search retrieves only documents that match the specified classification exactly. This is useful when you need to isolate documents at a specific classification level without including related categories.

Example: Searching for documents with classification Classified 1 will return only documents tagged as Classified 1, excluding General and other classifications.

A hierarchical classification search retrieves documents from the specified classification and all classifications below it in the hierarchy. This follows the access control pattern where higher-level classifications inherit access to lower-level information.

Example: Using the diagram above, a hierarchical search for Secret 1 will return documents tagged as:

  • Secret 1
  • Classified 1
  • Classified 2
  • General

This mirrors real-world access patterns where users with Secret 1 clearance can access all information at that level and below, but not Top-Secret or Secret 2 information.