feat: 完善文档分块参数配置
- 支持自定义正则匹配内容保留开关及配置持久化 - 约束分块重叠长度始终小于分块长度 - 补充中英文交互文案
This commit is contained in:
@@ -159,6 +159,9 @@
|
||||
"chunkSize": "SegmentLength",
|
||||
"overlapSize": "SegmentOverlap",
|
||||
"regex": "RegularExpression",
|
||||
"regexMatchHandling": "Matched content",
|
||||
"retainRegexMatch": "Keep in next chunk",
|
||||
"discardRegexMatch": "Discard",
|
||||
"document": "Document",
|
||||
"simpleDocumentSplitter": "SimpleDocumentSplitter",
|
||||
"simpleTokenizeSplitter": "SimpleTokenizeSplitter",
|
||||
|
||||
Reference in New Issue
Block a user