mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-08 08:28:02 +08:00
feat: add LLM-guided semantic rechunking for knowledge compilation (#17546)
This commit is contained in:
@@ -1900,6 +1900,12 @@ Example: Virtual Hosted Style`,
|
||||
rechunkByTreeLeaves: 'Re-chunk by tree leaves',
|
||||
rechunkByTreeLeavesTip:
|
||||
"Merge each leaf cluster's source chunks into a single replacement chunk. Originals are kept but marked unavailable for retrieval. Only one tree template per group may enable this.",
|
||||
rechunkInput: 'Re-chunk parser output',
|
||||
rechunkInputTip:
|
||||
'Let the LLM determine chunk boundaries based on the knowledge compilation task.',
|
||||
rechunkRules: 'Rechunking rules',
|
||||
rechunkRulesPlaceholder:
|
||||
'Describe how the LLM should group source chunks for this compilation task.',
|
||||
jsonPreview: 'JSON preview',
|
||||
processFlow: 'Process flow',
|
||||
processFlowComingSoon: 'Process flow preview coming soon',
|
||||
|
||||
@@ -1590,6 +1590,11 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取实体和关系
|
||||
rechunkByTreeLeaves: '按树叶重新分块',
|
||||
rechunkByTreeLeavesTip:
|
||||
'将每个叶簇的源数据块合并为单个替换数据块。原始数据块保留但标记为不可检索。每个分组最多只能有一个树模板启用此功能。',
|
||||
rechunkInput: '重新切分 Parser 输出',
|
||||
rechunkInputTip: '根据知识编译任务,由 LLM 决定 chunk 边界。',
|
||||
rechunkRules: 'Rechunk 规则',
|
||||
rechunkRulesPlaceholder:
|
||||
'描述此知识编译任务下,LLM 应如何合并和划分源 chunk。',
|
||||
jsonPreview: 'JSON 预览',
|
||||
processFlow: '流程视图',
|
||||
processFlowComingSoon: '流程视图预览即将到来',
|
||||
|
||||
Reference in New Issue
Block a user