deb422d03e
Score formula: recall×0.8 + ndcg×0.2 → recall 4x more important index: CHUNK_SIZE 256→384 (sweet spot, not too small, not too large) search: DENSE 80→50, SPARSE 200→150, RETRIEVE 150→100, RERANK 10→15 Fewer candidates = less noise = better recall Lotus experiments confirmed: 80/200/150 limits HURT vs 50/150/100. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| chunking.py | ||
| cleaning.py | ||
| Dockerfile | ||
| index_schemas.py | ||
| main.py | ||
| Makefile | ||
| rendering.py | ||
| requirements.txt | ||
| sparse.py | ||