Metadata-Version: 2.4
Name: zeta-mlx-embedding
Version: 0.3.2
Summary: Embedding model serving for Zeta MLX
Keywords: mlx,embedding,apple-silicon,bge,e5
Author: ZetaLab
Author-email: zeta9044@gmail.com
Requires-Python: >=3.10,<3.13
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: MacOS
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Provides-Extra: sentence-transformers
Requires-Dist: fastapi (>=0.115,<0.116)
Requires-Dist: numpy (>=1.26,<2.0)
Requires-Dist: sentence-transformers (>=3.0,<4.0) ; extra == "sentence-transformers"
Requires-Dist: uvicorn (>=0.32,<0.33)
Requires-Dist: zeta-mlx-core (>=0.3.2,<0.4.0)
Project-URL: Homepage, https://github.com/zeta9044/zeta-mlx
Project-URL: Repository, https://github.com/zeta9044/zeta-mlx
Description-Content-Type: text/markdown

# zeta-mlx-embedding

Embedding model serving for Zeta MLX platform.

## Installation

```bash
pip install zeta-mlx-embedding
```

## Features

- **OpenAI Compatible**: `/v1/embeddings` endpoint
- **Multilingual**: BGE-M3, E5-Large support
- **High Dimension**: 1024-dimensional embeddings

## Supported Models

| Model | Dimension | Description |
|-------|-----------|-------------|
| bge-m3 | 1024 | Korean/English optimized |
| multilingual-e5-large | 1024 | Multilingual |
| all-MiniLM-L6-v2 | 384 | Lightweight |

## Usage

```python
from zeta_mlx.embedding import EmbeddingEngine

engine = EmbeddingEngine("BAAI/bge-m3")
embeddings = engine.embed(["Hello", "안녕하세요"])
```

## Links

- [GitHub](https://github.com/zeta9044/zeta-mlx)
- [Documentation](https://github.com/zeta9044/zeta-mlx#readme)

