mirror of
https://github.com/HKUDS/LightRAG.git
synced 2025-12-13 15:57:29 +00:00
- Lowered max async LLM processes to 4 - Enabled LLM cache for entity extraction - Reduced max parallel insert to 2
- Lowered max async LLM processes to 4 - Enabled LLM cache for entity extraction - Reduced max parallel insert to 2