Feat/parent child retrieval (#12086)
Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: -LAN- <laipz8200@outlook.com> Co-authored-by: AkaraChen <akarachen@outlook.com> Co-authored-by: nite-knite <nkCoding@gmail.com> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: Warren Chen <warren.chen830@gmail.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: KVOJJJin <jzongcode@gmail.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com> Co-authored-by: Charlie.Wei <luowei@cvte.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: huayaoyue6 <huayaoyue@163.com> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Matsuda <yiyth.fcb6@gmail.com> Co-authored-by: shirochan <s.yusuke0711@gmail.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: Huỳnh Gia Bôi <boihuynh147@gmail.com> Co-authored-by: Julian Huynh <julian.huynh@immersio.io> Co-authored-by: Hash Brown <hi@xzd.me> Co-authored-by: 非法操作 <hjlarry@163.com> Co-authored-by: Kazuki Takamatsu <kazuki.takamatsu@chowagiken.co.jp> Co-authored-by: Trey Dong <1346650911@qq.com> Co-authored-by: VoidIsVoid <343750470@qq.com> Co-authored-by: Gimling <huangjl@ruyi.ai> Co-authored-by: xiandan-erizo <xiandan.erizo@gmail.com> Co-authored-by: Muneyuki Noguchi <nogu.dev@gmail.com> Co-authored-by: zhaobingshuang <1475195565@qq.com> Co-authored-by: zhaobs <zhaobs@cailian.net> Co-authored-by: suzuki.sh <s2terminal@users.noreply.github.com> Co-authored-by: Yingchun Lai <laiyingchun@apache.org> Co-authored-by: huanshare <huanshare@live.com> Co-authored-by: huanshare <liuhuan101@longfor.com> Co-authored-by: orangeclk <orangeclk@users.noreply.github.com> Co-authored-by: 문정현 <120004247+JungHyunMoon@users.noreply.github.com> Co-authored-by: barabicu <kztk533@gmail.com> Co-authored-by: Wei Mingzhi <whistler_wmz@users.sf.net> Co-authored-by: Paul van Oorschot <20116814+pvoo@users.noreply.github.com> Co-authored-by: zkyTech <zhangkunyuan@hotmail.com> Co-authored-by: zhangkunyuan <zhangkunyuan@cmhi.chinamobile.com> Co-authored-by: Tommy <34446820+Asterovim@users.noreply.github.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: Novice <857526207@qq.com> Co-authored-by: Novice Lee <novicelee@NovicedeMacBook-Pro.local> Co-authored-by: Novice Lee <novicelee@NoviPro.local> Co-authored-by: zxhlyh <16177003+zxhlyh@users.noreply.github.com> Co-authored-by: liuzhenghua <1090179900@qq.com> Co-authored-by: Jiang <65766008+AlwaysBluer@users.noreply.github.com> Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com> Co-authored-by: Joe <79627742+ZhouhaoJiang@users.noreply.github.com> Co-authored-by: Alok Shrivastwa <alok.shrivastwa@gmail.com> Co-authored-by: Alok Shrivastwa <Alok.Shrivastwa@microland.com> Co-authored-by: JasonVV <jasonwangiii@outlook.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com> Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com> Co-authored-by: NFish <douxc512@gmail.com> Co-authored-by: Junyan Qin <1010553892@qq.com> Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com> Co-authored-by: IWAI, Masaharu <iwai_masaharu@funkit.co.jp> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: luckylhb90 <luckylhb90@gmail.com> Co-authored-by: hobo.l <hobo.l@binance.com> Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
This commit is contained in:
parent
39ace9bdee
commit
2b2263a349
216 changed files with 9066 additions and 3116 deletions
|
|
@ -47,6 +47,7 @@ const translation = {
|
|||
notionSyncTitle: 'Notion 未绑定',
|
||||
notionSyncTip: '同步 Notion 内容前,须先绑定 Notion 空间',
|
||||
connect: '去绑定',
|
||||
cancel: '取消',
|
||||
button: '下一步',
|
||||
emptyDatasetCreation: '创建一个空知识库',
|
||||
modal: {
|
||||
|
|
@ -99,6 +100,16 @@ const translation = {
|
|||
autoDescription: '自动设置分段规则与预处理规则,如果不了解这些参数建议选择此项',
|
||||
custom: '自定义',
|
||||
customDescription: '自定义分段规则、分段长度以及预处理规则等参数',
|
||||
general: '通用',
|
||||
generalTip: '通用文本分块模式,检索和回忆的块是相同的',
|
||||
parentChild: '父子分段',
|
||||
parentChildTip: '使用父子模式时,子块用于检索,父块用作上下文',
|
||||
parentChunkForContext: '父块用作上下文',
|
||||
childChunkForRetrieval: '子块用于检索',
|
||||
paragraph: '段落',
|
||||
paragraphTip: '此模式根据分隔符和最大块长度将文本拆分为段落,使用拆分文本作为检索的父块',
|
||||
fullDoc: '全文',
|
||||
fullDocTip: '整个文档用作父块并直接检索。请注意,出于性能原因,超过10000个标记的文本将被自动截断。',
|
||||
separator: '分段标识符',
|
||||
separatorTip: '分隔符是用于分隔文本的字符。\\n\\n 和 \\n 是常用于分隔段落和行的分隔符。用逗号连接分隔符(\\n\\n,\\n),当段落超过最大块长度时,会按行进行分割。你也可以使用自定义的特殊分隔符(例如 ***)。',
|
||||
separatorPlaceholder: '\\n\\n 用于分段;\\n 用于分行',
|
||||
|
|
@ -111,19 +122,22 @@ const translation = {
|
|||
removeExtraSpaces: '替换掉连续的空格、换行符和制表符',
|
||||
removeUrlEmails: '删除所有 URL 和电子邮件地址',
|
||||
removeStopwords: '去除停用词,例如 “a”,“an”,“the” 等',
|
||||
preview: '确认并预览',
|
||||
preview: '预览',
|
||||
previewChunk: '预览块',
|
||||
reset: '重置',
|
||||
indexMode: '索引方式',
|
||||
qualified: '高质量',
|
||||
highQualityTip: '使用高质量模式进行嵌入后,无法切换回经济模式。',
|
||||
recommend: '推荐',
|
||||
qualifiedTip: '调用系统默认的嵌入接口进行处理,以在用户查询时提供更高的准确度',
|
||||
qualifiedTip: '调用嵌入模型处理文档以实现更精确的检索,可以帮助LLM生成高质量的答案。',
|
||||
warning: '请先完成模型供应商的 API KEY 设置。.',
|
||||
click: '前往设置',
|
||||
economical: '经济',
|
||||
economicalTip: '使用离线的向量引擎、关键词索引等方式,降低了准确度但无需花费 Token',
|
||||
economicalTip: '每个数据块使用10个关键词进行检索,不会消耗任何tokens,但会以降低检索准确性为代价。',
|
||||
QATitle: '采用 Q&A 分段模式',
|
||||
QATip: '开启后将会消耗额外的 token',
|
||||
QALanguage: '分段使用',
|
||||
useQALanguage: '使用 Q&A 分段,语言',
|
||||
estimateCost: '执行嵌入预估消耗',
|
||||
estimateSegment: '预估分段数',
|
||||
segmentCount: '段',
|
||||
|
|
@ -153,6 +167,15 @@ const translation = {
|
|||
indexSettingTip: '要更改索引方法和 embedding 模型,请转到',
|
||||
retrievalSettingTip: '要更改检索方法,请转到',
|
||||
datasetSettingLink: '知识库设置。',
|
||||
previewChunkTip: '点击左侧的“预览块”按钮来加载预览',
|
||||
previewChunkCount: '{{count}} 预估块',
|
||||
switch: '切换',
|
||||
qaSwitchHighQualityTipTitle: 'Q&A 格式需要高质量的索引方法',
|
||||
qaSwitchHighQualityTipContent: '目前,只有高质量的索引方法支持 Q&A 格式分块。您要切换到高质量模式吗?',
|
||||
notAvailableForParentChild: '不支持父子索引',
|
||||
notAvailableForQA: '不支持 Q&A 索引',
|
||||
parentChildDelimiterTip: '文本分隔符是用于分隔文本的字符。建议用 \n\n 将原始文档划分为较大的父级片段。您也可以自定义特殊分隔符。',
|
||||
parentChildChunkDelimiterTip: '文本分隔符是用于分隔文本的字符。建议使用 \n 将父级片段拆分为较小的子级片段。您也可以自定义特殊分隔符。',
|
||||
},
|
||||
stepThree: {
|
||||
creationTitle: '🎉 知识库已创建',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue