Defining the taxonomy

Define the taxonomy structure in the Flow Extract node covering the relationship between fields (the data points to be extracted) and field groups (a means of grouping fields under a single concept for processing).

Start by identifying all data points or fields that you want to extract from the documents. Then, organize the fields into a coherent structure using field groups. The fields defined under a field group can be predicted multiple times as different instances of that field group.

Note:

A taxonomy (an extraction schema) is a collection of all fields a model is prompted to extract, structured in a hierarchical manner using field groups.

Example of an extraction schema

Figure 1. Defining the extraction schema

Figure 2. Example of an extraction schema