Types of artifacts

First create or upload artifacts to use to train the models.

The models learn about the following types of artifacts that you add to the workspace:

• Type system

  A type system defines the entities and relationships between entities that matter to you. See Establishing a type system.

• Dictionaries

  A dictionary groups together words and phrases that should be treated equivalently by a model. See Creating dictionaries.

• Documents

  Documents serve a different purpose depending on whether you are creating a machine learning model or a rule-based model. See the following topics for more information:

  • Machine learning model documents: Adding documents for annotation
  • Rule-based model documents: Adding documents for defining rules

You can upload many of these artifacts from external resources, including artifacts that you downloaded from other Knowledge Studio workspaces. See Uploading resources from another workspace for information about uploading artifacts from other workspaces.

See Summary of inputs, outputs, and limitations for key facts about artifacts, such as size limits and supported file types for imported artifacts.