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

from docent import Docent

client = Docent()

state = client.get_clustering_state("my-collection-id", "rubric-123")
print(f"Job ID: {state.get('job_id')}")
print(f"Centroids: {len(state.get('centroids', []))}")

​
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

centroids = client.get_cluster_centroids("my-collection-id", "rubric-123")
for centroid in centroids:
    print(centroid)

​
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

assignments = client.get_cluster_assignments("my-collection-id", "rubric-123")
for centroid_id, result_ids in assignments.items():
    print(f"Cluster {centroid_id}: {len(result_ids)} results")

​
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.