vk_hackathon/search
q 7247248b27 Migrate to multi-file architecture: smarter chunking + fixed RERANK_LIMIT
index: message-based windowed chunking (5 msgs/1h gap), better unicode
cleaning, separate dense (with timestamps)/sparse content renderers,
BM25 preload on startup, ThreadPoolExecutor(4), UVICORN_WORKERS=4,
Dockerfile copies all *.py

search: proper multi-module structure (query_builder, retrieval, rerank,
aggregation), RERANK_LIMIT 60→15 (fixes 429 errors), extra dense vectors
for variants/hyde, date+asker metadata filters, httpx pool (100/20/30s),
BM25 preload on startup, Dockerfile copies all *.py

68/68 unit tests passing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-18 21:49:14 +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 Migrate to multi-file architecture: smarter chunking + fixed RERANK_LIMIT 2026-04-18 21:49:14 +03:00
Dockerfile Migrate to multi-file architecture: smarter chunking + fixed RERANK_LIMIT 2026-04-18 21:49:14 +03:00
main.py Migrate to multi-file architecture: smarter chunking + fixed RERANK_LIMIT 2026-04-18 21:49:14 +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 Migrate to multi-file architecture: smarter chunking + fixed RERANK_LIMIT 2026-04-18 21:49:14 +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