app.py

# from evaluate.utils import launch_gradio_widget
from tests import test_cases
from evaluate.utils.logging import get_logger
from evaluate.utils import (
    infer_gradio_input_types,
    parse_gradio_data,
    json_to_string_type,
    parse_readme,
    parse_test_cases,
)
from pathlib import Path

import evaluate
import sys
import evaluate

logger = get_logger(__name__)


def launch_gradio_widget(metric, test_cases):
    """Launches `metric` widget with Gradio."""

    try:
        import gradio as gr
    except ImportError as error:
        logger.error(
            "To create a metric widget with Gradio make sure gradio is installed."
        )
        raise error

    local_path = Path(sys.path[0])
    # if there are several input types, use first as default.
    if isinstance(metric.features, list):
        (feature_names, feature_types) = zip(*metric.features[0].items())
    else:
        (feature_names, feature_types) = zip(*metric.features.items())
    gradio_input_types = infer_gradio_input_types(feature_types)

    def compute(data):
        return metric.compute(**parse_gradio_data(data, gradio_input_types))

    iface = gr.Interface(
        fn=compute,
        inputs=gr.inputs.Dataframe(
            headers=feature_names,
            col_count=len(feature_names),
            row_count=5,
            datatype=json_to_string_type(gradio_input_types),
        ),
        outputs=gr.outputs.Textbox(label=metric.name),
        description=(
            metric.info.description
            + "\nIf this is a text-based metric, make sure to wrap you input in double quotes."
            " Alternatively you can use a JSON-formatted list as input."
        ),
        title=f"Metric: {metric.name}",
        article=parse_readme(local_path / "README.md"),
        # TODO: load test cases and use them to populate examples
        examples=[parse_test_cases(test_cases, feature_names, gradio_input_types)],
    )
    iface.launch()


module = evaluate.load("danieldux/metric_template_1")

launch_gradio_widget(module, test_cases)