Metrics grounded in science,
built by the community.

1from gaussia.metrics.toxicity import Toxicity
2from gaussia.core.retriever import Retriever
3from gaussia.schemas.common import Dataset, Batch
4
5# Define a custom retriever to load your data
6class MyRetriever(Retriever):
7    def load_dataset(self) -> list[Dataset]:
8        return [
9            Dataset(
10                session_id="session-1",
11                assistant_id="my-assistant",
12                language="english",
13                context="",
14                conversation=[
15                    Batch(
16                        qa_id="q1",
17                        query="Tell me about AI safety",
18                        assistant="AI safety is important...",
19                    )
20                ]
21            )
22        ]
23
24# Run the toxicity metric
25results = Toxicity.run(
26    MyRetriever,
27    group_prototypes={
28        "gender": ["women", "men", "female", "male"],
29        "race": ["Asian", "African", "European"],
30    },
31    verbose=True,
32)
33
34# Analyze results
35for metric in results:
36    print(f"DIDT Score: {metric.group_profiling.frequentist.DIDT}")