Metadata-Version: 2.4
Name: guardrails-ai-detect-jailbreak
Version: 0.2.1a1
Summary: Detects attempts to circumvent safeguards in model conditioning.
Author: Guardrails AI
License-Expression: MIT
Project-URL: Homepage, https://guardrailsai.com
Project-URL: Repository, https://github.com/guardrails-ai/guardrails-hub-monorepo/tree/main/detect_jailbreak/py
Project-URL: Documentation, https://github.com/guardrails-ai/guardrails-hub-monorepo/blob/main/detect_jailbreak/py/README.md
Requires-Python: <4,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: guardrails-ai>=0.5.10
Requires-Dist: torch>=2.4
Requires-Dist: transformers>=4.40
Requires-Dist: cached_path>=1.6
Provides-Extra: dev
Requires-Dist: ruff; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: coverage>=7.6.12; extra == "dev"
Requires-Dist: pyright[nodejs]>=1.1.396; extra == "dev"
Dynamic: license-file

# guardrails-ai-detect-jailbreak

Detects attempts to circumvent safeguards in model conditioning.

## Installation

```bash
pip install guardrails-ai-detect-jailbreak
```

This validator ships local models. After installing, run the post-install step to download them:

```bash
python -m guardrails_ai.detect_jailbreak.post_install
```

## Usage

```python
from guardrails import Guard
from guardrails_ai.detect_jailbreak import DetectJailbreak

guard = Guard().use(DetectJailbreak)
```

## License

MIT — © Guardrails AI.
