提升RAGLight检索质量可通过3个维度实现：
- parameterization: Enlargement
k值（如设为8-10）可检索更多文档片段，但会增加计算耗时。建议从k=5开始逐步测试 - Mode Selection::
- start using
RAT模式pass (a bill or inspection etc)reflection参数（推荐值2-3）增加反思步骤，提升逻辑严密性 - adoption
Agentic RAG(used form a nominal expression)max_steps参数实现多轮检索优化
- start using
- embedding model：替换默认向量模型为
all-MiniLM-L6-v2等高质量选项，需在VectorStoreConfigspecified inembedding_modelcap (a poem)provider=Settings.HUGGINGFACE
注意：模型选择应考虑硬件性能，大型嵌入模型可能显著增加内存消耗。
This answer comes from the articleRAGLight: Lightweight Retrieval Augmentation Generation Python LibraryThe
May not be reproduced without permission:AI productivity tools " How to optimize the relevance and accuracy of RAGLight search results?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil