Metadata-Version: 2.4
Name: rag-forge-evaluator
Version: 0.1.0
Summary: Evaluation engine: RAGAS, DeepEval, LLM-as-Judge, and audit report generation
Project-URL: Homepage, https://github.com/hallengray/rag-forge
Project-URL: Repository, https://github.com/hallengray/rag-forge
Project-URL: Issues, https://github.com/hallengray/rag-forge/issues
Project-URL: Documentation, https://github.com/hallengray/rag-forge#readme
Author: Femi Adedayo
License-Expression: MIT
Keywords: deepeval,evaluation,llm-as-judge,rag,ragas,rmm
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Requires-Dist: anthropic>=0.30
Requires-Dist: jinja2>=3.1
Requires-Dist: openai>=1.30
Requires-Dist: pydantic>=2.0
Provides-Extra: deepeval
Requires-Dist: deepeval>=1.0; extra == 'deepeval'
Provides-Extra: pdf
Requires-Dist: playwright>=1.40; extra == 'pdf'
Provides-Extra: ragas
Requires-Dist: ragas>=0.2; extra == 'ragas'
Description-Content-Type: text/markdown

# rag-forge-evaluator

RAG pipeline evaluation engine for the RAG-Forge toolkit: RAGAS, DeepEval, LLM-as-Judge, and the RAG Maturity Model.

## Installation

```bash
pip install rag-forge-evaluator
```

## Usage

```python
from rag_forge_evaluator.assess import RMMAssessor

assessor = RMMAssessor()
result = assessor.assess(config={
    "retrieval_strategy": "hybrid",
    "input_guard_configured": True,
    "output_guard_configured": True,
})
print(result.badge)  # e.g., "RMM-3 Better Trust"
```

## Features

- RMM (RAG Maturity Model) scoring (levels 0-5)
- RAGAS, DeepEval, and LLM-as-Judge evaluators
- Golden set management with traffic sampling
- Cost estimation
- HTML and PDF report generation

## License

MIT
