Hariharan05/ragone-1810

RAGOne

RAGOne is a ModernBERT-based model for evaluating retrieved context in Retrieval-Augmented Generation (RAG) pipelines.

Installation

pip install -r requirements.txt

Usage

from ragone import RAGOne

model = RAGOne.from_pretrained("YOUR_USERNAME/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["prediction"])
print(result["scores"])
print(result["latency_ms"])

The package includes the fine-tuned encoder, scorer, tokenizer, configuration, and inference code. It does not need to download the original ModernBERT checkpoint separately.