🦅 Phoenix is out with our latest release!
Making sense of embeddings can be overwhelming. With density-based clustering, you can start to reason about your embedding's higher-dimensional representation in meaningful groups.
Clusters provide an "auto-lasso" 🪢, segmenting your unstructured data into semantically similar cohorts. We are going to continue to build analytics on top of clusters to help identify groups of embeddings to provide well-defined heuristics for fine-tuning and retraining.
Tuning your HDBSCAN parameters for clustering is now easier than ever. Try it out in our latest release 0.0.23.