Skip to main content
We no longer recommend clustering rubric evaluations as a primary workflow. The Docent plugin generates reduce-style Reading steps for clustering inside an Analysis Plan. This SDK reference is kept for users with existing clustering data.
After running a rubric evaluation, Docent can cluster judge results to identify common patterns. See Search and Clustering for a walkthrough.

Get Clustering State

Parameters

collection_id
str
required
ID of the collection.
rubric_id
str
required
ID of the rubric.

Returns

state
dict
Clustering state.

Get Cluster Centroids

Parameters

collection_id
str
required
ID of the collection.
rubric_id
str
required
ID of the rubric.

Returns

centroids
list[dict]
List of centroid information dictionaries.

Get Cluster Assignments

Parameters

collection_id
str
required
ID of the collection.
rubric_id
str
required
ID of the rubric.

Returns

assignments
dict[str, list[str]]
Mapping of centroid IDs to lists of judge result IDs belonging to that cluster.