embedding-clusterer 0.1.0

Embedding-based semantic clustering for LLM responses using KMedoids + Davies-Bouldin

Embedding Clusterer

A semantic clustering library for grouping LLM responses using embedding-based methods with KMedoids and Davies-Bouldin Index for cluster evaluation.

Installation

pip install embedding-clusterer

Features

• Embedding-based Clustering: Use sentence embeddings to group similar responses
• KMedoids Algorithm: Robust clustering with actual representative samples
• Davies-Bouldin Index: Automatic cluster evaluation and quality assessment
• Transformer Models: Compatible with Hugging Face sentence-transformers

Usage

from embedding_clusterer import SemanticClusterer

clusterer = SemanticClusterer()
clusters = clusterer.cluster(texts, num_clusters=3)

Dependencies

• numpy
• scikit-learn
• sentence-transformers

License

See LICENSE file for details.