Evaluation Result

The EvalResult object, generated by the evaluate function, is versatile and can be easily converted to various data types such as dictionaries and pandas dataframe, facilitating seamless integration with different systems and workflows.

from ragrank import evaluate
from ragrank.evaluation import EvalResult
from ragrank.dataset import DataNode

data = DataNode(
    question="What is the tallest mountain in the world?",
    context=[
        "Mount Everest is the tallest mountain above sea level.",
        "It is located in the Himalayas.",
    ],
    response="The tallest mountain in the world is Mount Everest.",
)

result:EvalResult = evaluate(
    data ,
)

print(result.to_dict())

Attributes of the EvalResult:

• llm: The language model used for evaluation.

• metrics: List of metrics used for evaluation.

• dataset: The dataset used for evaluation.

• scores: List of scores for each metric.

• response_time: Response time for the evaluation process.

Methods:

• to_dict() : Convert the data into dict format

• to_dataframe() : Convert the data into a pandas dataframe