eed820df1b
The runner passed the dataset's path to every arm, which opens one database and is what makes `--db` meaningful. A run over `lancedb.databases` has to pass none instead, so the client resolves the set, and `DatasetSpec.covers_a_set` is the one place that decides which of the two a run is. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_benchmark.py | ||
| test_capability_runner.py | ||
| test_citation_evaluators.py | ||
| test_config.py | ||
| test_conversation_evaluator.py | ||
| test_datasets.py | ||
| test_evaluators.py | ||
| test_mtrag.py | ||
| test_numbers.py | ||
| test_reference_configs.py | ||
| test_submission.py | ||