Metadata-Version: 2.4
Name: ragone-ai
Version: 0.1.0
Summary: ModernBERT-based RAG evaluation model
Author: Hariharan Suthan
License-Expression: MIT
Keywords: RAG,retrieval-augmented-generation,evaluation,ModernBERT,NLP
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.1
Requires-Dist: transformers>=4.45
Requires-Dist: huggingface_hub>=0.25
Requires-Dist: safetensors>=0.4
Dynamic: license-file

# RAGOne

RAGOne evaluates retrieved context for RAG pipelines using a
fine-tuned ModernBERT encoder and a trained scoring head.

## Install

```bash
pip install ragone-ai
```

## Quick start

```python
from ragone import RAGOne

model = RAGOne.from_pretrained("Hariharan05/ragone")

result = model.predict(
    query="What is the refund period?",
    context="Customers can request a refund within 30 days.",
    task="answerability",
    options=["yes", "no"],
)

print(result)
```

The model files are downloaded from Hugging Face on first use.
The PyPI package contains inference code, not the model weights.

Supported tasks include relevance, answerability, evidence quality,
and contradiction. Use the candidate labels appropriate for your
training dataset.
