Reduce
Cluster
Cluster documents by embedding similarity to discover themes
Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.
Configuration
string
Clustering algorithm: 'hdbscan' (auto K, recommended), 'kmeans' (requires n_clusters), 'dbscan', 'agglomerative', 'spectral', 'gaussian_mixture'.
integer | null
Number of clusters (required for kmeans, spectral, agglomerative).
integer
Minimum docs to form a cluster (HDBSCAN/DBSCAN).
string | null
Feature URI to cluster on. Auto-detected from upstream feature_search if not set.
string
Output format: 'clusters' (K summaries), 'labeled' (N docs with cluster_id), 'representatives' (K best docs).
integer
Max members per cluster in output.
Output
No output yet
Configure the stage parameters and click "Run Stage" to see the simulated output.