vk_hackathon/search
q d5ed8c7764 Improve search quality: RERANK_LIMIT 10→60, search_text for dense, variants+hyde multi-vector
- RERANK_LIMIT 10→60: rerank more candidates → better NDCG ordering
- Dense query uses search_text if available (semantically richer than text)
- Sparse query always appends keywords on top of base text
- Multi-vector: use variants[:2] + hyde[:2] as extra dense queries
  (previously only hyde[:2])
- Index UVICORN_WORKERS 8→4: matches 4-core constraint, saves ~1GB RAM

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-18 19:04:23 +03:00
..
__init__.py Refactor index and search services 2026-04-18 13:57:15 +03:00
aggregation.py Add logviewer project and fix Docker imports 2026-04-18 15:26:11 +03:00
config.py Refactor index and search services 2026-04-18 13:57:15 +03:00
Dockerfile Port index and search logic from working Lotus reference implementation 2026-04-18 18:32:41 +03:00
main.py Improve search quality: RERANK_LIMIT 10→60, search_text for dense, variants+hyde multi-vector 2026-04-18 19:04:23 +03:00
Makefile Fix date_range filter: use DatetimeRange for RFC3339 strings; set TEAM_ID=35230 in Makefiles, add release target 2026-04-18 16:26:14 +03:00
query_builder.py Clean up search: proper retry loop, batch embedding, remove duplicate wrapper 2026-04-18 16:50:34 +03:00
requirements.txt Source VK code 2026-04-18 10:51:43 +03:00
rerank.py Clean up search: proper retry loop, batch embedding, remove duplicate wrapper 2026-04-18 16:50:34 +03:00
retrieval.py Fix date_range filter: use DatetimeRange for RFC3339 strings; set TEAM_ID=35230 in Makefiles, add release target 2026-04-18 16:26:14 +03:00
schemas.py Refactor index and search services 2026-04-18 13:57:15 +03:00