How To Cluster Data In Relevance AI

Relevance AI provides you with a no-code workflow to cluster your vectorized data with a few clicks. Make sure to follow the vectorize workflow guide if your dataset does not yet include vectors.

Once you have uploaded and vectorized your data, select your dataset and click on Cluster workflow. The image below shows how to cluster a dataset based on the description field using the Kmeans algorithm.

Relevance AI - cluster workflow setup for clustering data using the Kmeans algorithm.Relevance AI - cluster workflow setup for clustering data using the Kmeans algorithm.

Relevance AI - cluster workflow setup for clustering data using the Kmeans algorithm.

After running this workflow, clustering results are automatically added to your dataset under a new field (cluster.descriptionmpnet_vector.kmeans-10 for the example used in this guide). Check the results under the Dataset -> Monitor -> Clusters.

You are now ready to set up your Explorer dashboard.


Related Articles (coming soon)

How To Choose The Optimal Number Of Clusters

How To Label Clusters

How To Merge Clusters

How To Move Responses To Different Clusters

Tips To Improve Cluster Accuracy

Tips To Setup A Cluster Dashboard: Charts and Metrics

How To Export Clusters


Did this page help you?