ragflow/rag
He Wang badf33e3b9
feat: enhance OBConnection.search (#11876)
### What problem does this PR solve?

Enhance OBConnection.search for better performance. Main changes:
1. Use string type of vector array in distance func for better parsing
performance.
2. Manually set max_connections as pool size instead of using default
value.
3. Set 'fulltext_search_columns' when starting.
4. Cache the results of the table existence check (we will never drop
the table).
5. Remove unused 'group_results' logic.
6. Add the `USE_FULLTEXT_FIRST_FUSION_SEARCH` flag, and the
corresponding fusion search SQL when it's false.

### Type of change
- [x] Performance Improvement
2025-12-10 19:13:37 +08:00
..
app Fix:csv parse in Table (#11870) 2025-12-10 16:44:06 +08:00
flow Refa:replace trio with asyncio (#11831) 2025-12-09 19:23:14 +08:00
llm Fix: duplicate output by async_chat_streamly (#11842) 2025-12-09 19:21:52 +08:00
nlp Fix: parent-child chunking method (#11810) 2025-12-09 09:34:01 +08:00
prompts Refa:replace trio with asyncio (#11831) 2025-12-09 19:23:14 +08:00
res Remove huqie.txt from RAGFflow and bump infinity to 0.6.10 (#11661) 2025-12-04 14:53:57 +08:00
svr Refa:replace trio with asyncio (#11831) 2025-12-09 19:23:14 +08:00
utils feat: enhance OBConnection.search (#11876) 2025-12-10 19:13:37 +08:00
__init__.py Fix: incorrect async chat streamly output (#11679) 2025-12-03 11:15:45 +08:00
benchmark.py Move api.settings to common.settings (#11036) 2025-11-06 09:36:38 +08:00
raptor.py Refa:replace trio with asyncio (#11831) 2025-12-09 19:23:14 +08:00
settings.py Move api.settings to common.settings (#11036) 2025-11-06 09:36:38 +08:00