Stephen Hu fb77f9917b Refactor: Use Input Length In DefaultRerank (#9516) ... ### What problem does this PR solve? 1. Use input length to prepare res 2. Adjust torch_empty_cache code location ### Type of change - [x] Refactoring - [x] Performance Improvement		2025-08-18 10:00:27 +08:00
..
app	Fix: unexpected truncated Excel files (#9500)	2025-08-15 17:00:34 +08:00
llm	Refactor: Use Input Length In DefaultRerank (#9516)	2025-08-18 10:00:27 +08:00
nlp	Feat: add meta data filter. (#9405)	2025-08-12 14:12:56 +08:00
prompts	Refa: split services about llm. (#9450)	2025-08-13 16:41:01 +08:00
res	Refa: add result to callback for agent tool use. (#9137)	2025-08-01 21:49:39 +08:00
svr	Feat: add citation option to agent and enlarge the timeouts. (#9484)	2025-08-15 10:05:01 +08:00
utils	Fix: no doc hits after meta data filter. (#9435)	2025-08-13 12:43:31 +08:00
__init__.py	Update comments (#4569)	2025-01-21 20:52:28 +08:00
benchmark.py	Refactor embedding batch_size (#3825)	2024-12-03 16:22:39 +08:00
raptor.py	Refa: remove temperature since some LLMs fail to support. (#8981)	2025-07-23 10:17:04 +08:00
settings.py	Feat: make document parsing and embedding batch sizes configurable via environment variables (#8266)	2025-06-16 13:40:47 +08:00