409f60e1bf
Hybrid search inside one database fuses its own vector and FTS rankings with lancedb's RRFReranker over exactly the requested limit, and both branch queries derive from the same inner query, so there is no branch-depth knob. Below roughly 50 candidates the two rankings stop overlapping, nothing sums, and the fusion degenerates: measured recall@5 on a single database was 0.000 at fetch 5, 10 and 20, then 0.267 at 50 and 0.350 at 100. A dataset's retrieval_limit therefore fixes which regime it measures, and comparing regimes would otherwise need one dataset per depth. Claude-Session: https://claude.ai/code/session_01WhudUtZm6qqiuv8Y1sbwSc |
||
|---|---|---|
| .. | ||
| __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_mtrag_federated.py | ||
| test_numbers.py | ||
| test_reference_configs.py | ||
| test_submission.py | ||