Metadata-Version: 2.4
Name: embedding-clusterer
Version: 0.1.0
Summary: Embedding-based semantic clustering for LLM responses using KMedoids + Davies-Bouldin
Author-email: Akshiya <raveendiran.21@cse.mrt.ac.lk>
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: sentence-transformers

# Embedding Clusterer

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

## Installation

```bash
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

```python
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.

