Brian920128 Doc Retrieve Metrics

---
name: brian920128-doc-retrieve-metrics
description: Compute brian920128/doc_retrieve_metrics via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of brian920128/doc_retrieve_metrics.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: brian920128/doc_retrieve_metrics
  source: library_introspection
---

# brian920128-doc-retrieve-metrics

> Metric `brian920128/doc_retrieve_metrics` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `brian920128/doc_retrieve_metrics` or wants HF evaluate's canonical version.

## Recipe

```python
import evaluate
metric = evaluate.load("brian920128/doc_retrieve_metrics")
result = metric.compute(predictions=preds, references=refs)
print(result)
```

## Don'ts

- Don't assume your in-house `brian920128/doc_retrieve_metrics` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.