Metadata-Version: 2.4
Name: zeta-mlx-rag
Version: 0.3.2
Summary: RAG (Retrieval-Augmented Generation) for Zeta MLX
Keywords: mlx,rag,retrieval,apple-silicon
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: embeddings
Requires-Dist: numpy (>=1.26,<2.0)
Requires-Dist: sentence-transformers (>=3.0,<4.0) ; extra == "embeddings"
Requires-Dist: zeta-mlx-core (>=0.3.2,<0.4.0)
Requires-Dist: zeta-mlx-inference (>=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-rag

RAG (Retrieval-Augmented Generation) pipeline for Zeta MLX.

## Installation

```bash
pip install zeta-mlx-rag
```

## Features

- **Document Processing**: Text chunking and preprocessing
- **Embeddings**: Integration with zeta-mlx-embedding
- **Retrieval**: Vector similarity search
- **Generation**: Context-aware LLM responses

## Usage

```python
from zeta_mlx.rag import RAGPipeline

pipeline = RAGPipeline(
    embedding_model="bge-m3",
    llm_model="qwen3-8b"
)

# Add documents
pipeline.add_documents(["doc1.txt", "doc2.txt"])

# Query
response = pipeline.query("What is MLX?")
```

## Links

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

