Sign in
Clusters

Compute new clusters

Starts a background task to compute how the data in an embedded storage bucket is clustered. This helps identify common themes and patterns in the data.

post/ai/clusters

Request body

bucketstring required

The embedded storage bucket to compute the clusters from. The bucket must already be embedded.

prefixstring

Prefix to filter whcih files in the buckets are included.

filesstring[]

Array of files to filter which are included.

min_cluster_sizeinteger

Smallest number of related text chunks to qualify as a cluster. Top-level clusters should be thought of as identifying broad themes in your data.

min_subcluster_sizeinteger

Smallest number of related text chunks to qualify as a sub-cluster. Sub-clusters should be thought of as identifying more specific topics within a broader theme.

Response

Successful Response

Changes

No changes recorded. 1 of the 99 revisions has no diff computed, so it could not be searched.