Metadata-Version: 2.4
Name: lexiredact
Version: 0.2.0
Summary: Privacy-preserving RAG ingestion middleware with dual-pipeline processing
Project-URL: Homepage, https://github.com/baihelahusain/lexiredact
Project-URL: Repository, https://github.com/baihelahusain/LexiRedact
Project-URL: Issues, https://github.com/baihelahusain/LexiRedact/issues
Project-URL: Documentation, https://github.com/baihelahusain/LexiRedact
Author: Baihela Abid Hussain, Shwetan Bharat Londhe, Varad Limbkar
License: MIT
License-File: LICENSE
Keywords: embeddings,llm,pii,privacy,rag,redaction,retrieval-augmented-generation,security,vector-database
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Security
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Requires-Dist: pydantic<3.0,>=2.0
Requires-Dist: pyyaml<7.0,>=6.0
Provides-Extra: all
Requires-Dist: chromadb>=0.4; extra == 'all'
Requires-Dist: click>=8.0; extra == 'all'
Requires-Dist: presidio-analyzer; extra == 'all'
Requires-Dist: presidio-anonymizer; extra == 'all'
Requires-Dist: redis>=5.0; extra == 'all'
Requires-Dist: sentence-transformers>=2.0; extra == 'all'
Requires-Dist: spacy; extra == 'all'
Provides-Extra: cache
Requires-Dist: redis>=5.0; extra == 'cache'
Provides-Extra: cli
Requires-Dist: click>=8.0; extra == 'cli'
Provides-Extra: dev
Requires-Dist: mypy>=1.10; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Provides-Extra: embed
Requires-Dist: sentence-transformers>=2.0; extra == 'embed'
Provides-Extra: pii
Requires-Dist: presidio-analyzer; extra == 'pii'
Requires-Dist: presidio-anonymizer; extra == 'pii'
Requires-Dist: spacy; extra == 'pii'
Provides-Extra: store
Requires-Dist: chromadb>=0.4; extra == 'store'
Description-Content-Type: text/markdown

# LexiRedact

LexiRedact is a privacy-preserving RAG ingestion middleware package for detecting and redacting PII before content is embedded and written to a vector store.

## Installation

```bash
pip install lexiredact
```

Optional dependency groups are available for specific integrations:

```bash
pip install "lexiredact[pii,embed,store,cache,cli]"
```

## Quick Start

```python
from lexiredact import LexiredactPipeline, load_config

config = load_config("lexiredact_config.yaml")
pipeline = LexiredactPipeline(config)
```

## CLI

```bash
lexiredact --help
```

## Release

This project publishes to PyPI from GitHub Actions when a version tag is pushed:

```bash
git tag v0.0.2
git push origin v0.0.2
```

The PyPI project must be configured for Trusted Publishing with the `pypi` environment and the `.github/workflows/publish.yml` workflow.
