mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
DOC: Miscellaneous UI and editorial updates (#7324)
### What problem does this PR solve? ### Type of change - [x] Documentation Update
This commit is contained in:
writinwaters
@ -100,7 +100,7 @@ export default {
|
||||
webCrawl: 'Web Crawl',
|
||||
chunkNumber: 'Chunk Number',
|
||||
uploadDate: 'Upload Date',
|
||||
chunkMethod: 'Chunk Method',
|
||||
chunkMethod: 'Chunking method',
|
||||
enabled: 'Enable',
|
||||
disabled: 'Disable',
|
||||
action: 'Action',
|
||||
@ -166,7 +166,7 @@ export default {
|
||||
delimiterTip:
|
||||
'A delimiter or separator can consist of one or multiple special characters. If it is multiple characters, ensure they are enclosed in backticks( ``). For example, if you configure your delimiters like this: \\n`##`;, then your texts will be separated at line breaks, double hash symbols (##), and semicolons.',
|
||||
html4excel: 'Excel to HTML',
|
||||
html4excelTip: `Use with the General chunk method. When disabled, spreadsheets (XLSX or XLS(Excel97~2003)) in the knowledge base will be parsed into key-value pairs. When enabled, they will be parsed into HTML tables, splitting every 12 rows if the original table has more than 12 rows.`,
|
||||
html4excelTip: `Use with the General chunking method. When disabled, spreadsheets (XLSX or XLS(Excel97~2003)) in the knowledge base will be parsed into key-value pairs. When enabled, they will be parsed into HTML tables, splitting every 12 rows if the original table has more than 12 rows.`,
|
||||
autoKeywords: 'Auto-keyword',
|
||||
autoKeywordsTip: `Automatically extract N keywords for each chunk to increase their ranking for queries containing those keywords. Be aware that extra tokens will be consumed by the chat model specified in 'System model settings'. You can check or update the added keywords for a chunk from the chunk list. `,
|
||||
autoQuestions: 'Auto-question',
|
||||
@ -201,7 +201,7 @@ export default {
|
||||
},
|
||||
knowledgeConfiguration: {
|
||||
titleDescription:
|
||||
'Update your knowledge base configuration here, particularly the chunk method.',
|
||||
'Update your knowledge base configuration here, particularly the chunking method.',
|
||||
name: 'Knowledge base name',
|
||||
photo: 'Knowledge base photo',
|
||||
description: 'Description',
|
||||
@ -218,19 +218,19 @@ export default {
|
||||
"If it is set to 'Team', all your team members will be able to manage the knowledge base.",
|
||||
chunkTokenNumberTip:
|
||||
'It kind of sets the token threshold for a creating a chunk. A segment with fewer tokens than this threshold will be combined with the following segments until the token count exceeds the threshold, at which point a chunk is created. No new chunk is created unless a delimiter is encountered, even if the threshold is exceeded.',
|
||||
chunkMethod: 'Chunk method',
|
||||
chunkMethod: 'Chunking method',
|
||||
chunkMethodTip: 'View the tips on the right.',
|
||||
upload: 'Upload',
|
||||
english: 'English',
|
||||
chinese: 'Chinese',
|
||||
portugueseBr: 'Portuguese (Brazil)',
|
||||
embeddingModelPlaceholder: 'Please select a embedding model.',
|
||||
chunkMethodPlaceholder: 'Please select a chunk method.',
|
||||
chunkMethodPlaceholder: 'Please select a chunking method.',
|
||||
save: 'Save',
|
||||
me: 'Only me',
|
||||
team: 'Team',
|
||||
cancel: 'Cancel',
|
||||
methodTitle: 'Chunk method description',
|
||||
methodTitle: 'Chunking method description',
|
||||
methodExamples: 'Examples',
|
||||
methodExamplesDescription:
|
||||
'The following screenshots are provided for clarity.',
|
||||
@ -258,10 +258,10 @@ export default {
|
||||
However, it also increases the context for AI conversations and adds to the computational cost for the LLM. So during a conversation, consider reducing the value of ‘<b>topN</b>’.</p>`,
|
||||
presentation: `<p>Supported file formats are <b>PDF</b>, <b>PPTX</b>.</p><p>
|
||||
Every page in the slides is treated as a chunk, with its thumbnail image stored.</p><p>
|
||||
<i>This chunk method is automatically applied to all uploaded PPT files, so you do not need to specify it manually.</i></p>`,
|
||||
<i>This chunking method is automatically applied to all uploaded PPT files, so you do not need to specify it manually.</i></p>`,
|
||||
qa: `
|
||||
<p>
|
||||
This chunk method supports <b>XLSX</b> and <b>CSV/TXT</b> file formats.
|
||||
This chunking method supports <b>XLSX</b> and <b>CSV/TXT</b> file formats.
|
||||
</p>
|
||||
<li>
|
||||
If a file is in <b>XLSX</b> or <b>XLS (Excel97~2003)</b> format, it should contain two columns without headers: one for questions and the other for answers, with the question column preceding the answer column. Multiple sheets are
|
||||
@ -314,8 +314,8 @@ export default {
|
||||
<p>This approach chunks files using the 'naive'/'General' method. It splits a document into segments and then combines adjacent segments until the token count exceeds the threshold specified by 'Chunk token number for text', at which point a chunk is created.</p>
|
||||
<p>The chunks are then fed to the LLM to extract entities and relationships for a knowledge graph and a mind map.</p>
|
||||
<p>Ensure that you set the <b>Entity types</b>.</p>`,
|
||||
tag: `<p>A knowledge base using the 'Tag' chunk method functions as a tag set. Other knowledge bases can use it to tag their own chunks, and queries to these knowledge bases will also be tagged using this tag set.</p>
|
||||
<p>Knowledge base using 'Tag' as a chunk method will <b>NOT</b> be involved in a Retrieval-Augmented Generation (RAG) process.</p>
|
||||
tag: `<p>A knowledge base using the 'Tag' chunking method functions as a tag set. Other knowledge bases can use it to tag their own chunks, and queries to these knowledge bases will also be tagged using this tag set.</p>
|
||||
<p>Knowledge base using 'Tag' as a chunking method will <b>NOT</b> be involved in a Retrieval-Augmented Generation (RAG) process.</p>
|
||||
<p>Each chunk in this knowledge base is an independent description-tag pair.</p>
|
||||
<p>Supported file formats include <b>XLSX</b> and <b>CSV/TXT</b>:</p>
|
||||
<p>If a file is in <b>XLSX</b> format, it should contain two columns without headers: one for tag descriptions and the other for tag names, with the Description column preceding the Tag column. Multiple sheets are acceptable, provided the columns are properly structured.</p>
|
||||
@ -1216,7 +1216,7 @@ This delimiter is used to split the input text into several text pieces echo of
|
||||
}`,
|
||||
datatype: 'MINE type of the HTTP request',
|
||||
insertVariableTip: `Enter / Insert variables`,
|
||||
historyversion: 'History version',
|
||||
historyversion: 'Version history',
|
||||
filename: 'File name',
|
||||
version: {
|
||||
created: 'Created',
|
||||
@ -1226,14 +1226,14 @@ This delimiter is used to split the input text into several text pieces echo of
|
||||
version: 'Version',
|
||||
select: 'No version selected',
|
||||
},
|
||||
setting: 'Setting',
|
||||
setting: 'Settings',
|
||||
settings: {
|
||||
agentSetting: 'Agent Setting',
|
||||
agentSetting: 'Agent settings',
|
||||
title: 'title',
|
||||
description: 'description',
|
||||
upload: 'Upload',
|
||||
photo: 'Photo',
|
||||
permissions: 'Permission',
|
||||
permissions: 'Permissions',
|
||||
permissionsTip: 'You can set the permissions of the team members here.',
|
||||
me: 'me',
|
||||
team: 'Team',
|
||||
|
||||
@ -162,7 +162,7 @@ export default {
|
||||
topKTip: `與 Rerank 模型配合使用，用於設定傳給 Rerank 模型的文本塊數量。`,
|
||||
delimiter: `文字分段標識符`,
|
||||
delimiterTip:
|
||||
'支持多字符作為分隔符，多字符用 `` 分隔符包裹。若配置成：\\n`##`; 系統將首先使用換行符、兩個#號以及分號先對文本進行分割，隨後再對分得的小文本塊按照「建议文本块大小」設定的大小進行拼裝。在设置文本分段標識符之前，請確保您已理解上述文本分段切片機制。',
|
||||
'支持多字符作為分隔符，多字符用兩個反引號 \\`\\` 分隔符包裹。若配置成：\\n`##`; 系統將首先使用換行符、兩個#號以及分號先對文本進行分割，隨後再對分得的小文本塊按照「建议文本块大小」設定的大小進行拼裝。在设置文本分段標識符之前，請確保您已理解上述文本分段切片機制。',
|
||||
html4excel: '表格轉HTML',
|
||||
html4excelTip: `與 General 切片方法配合使用。未開啟狀態下，表格檔案（XLSX、XLS（Excel97~2003）會按行解析為鍵值對。開啟後，表格檔案會被解析為 HTML 表格。若原始表格超過 12 行，系統會自動按每 12 行拆分為多個 HTML 表格。`,
|
||||
autoKeywords: '自動關鍵字',
|
||||
|
||||
@ -162,7 +162,7 @@ export default {
|
||||
topKTip: `与 Rerank 模型配合使用，用于设置传给 Rerank 模型的文本块数量。`,
|
||||
delimiter: `文本分段标识符`,
|
||||
delimiterTip:
|
||||
'支持多字符作为分隔符，多字符用 `` 分隔符包裹。若配置成：\\n`##`; 系统将首先使用换行符、两个#号以及分号先对文本进行分割，随后再对分得的小文本块按照「建议文本块大小」设定的大小进行拼装。在设置文本分段标识符前请确保理解上述文本分段切片机制。',
|
||||
'支持多字符作为分隔符，多字符用两个反引号 \\`\\` 分隔符包裹。若配置成：\\n`##`; 系统将首先使用换行符、两个#号以及分号先对文本进行分割，随后再对分得的小文本块按照「建议文本块大小」设定的大小进行拼装。在设置文本分段标识符前请确保理解上述文本分段切片机制。',
|
||||
html4excel: '表格转HTML',
|
||||
html4excelTip: `与 General 切片方法配合使用。未开启状态下，表格文件（XLSX、XLS（Excel97~2003））会按行解析为键值对。开启后，表格文件会被解析为 HTML 表格。若原始表格超过 12 行，系统会自动按每 12 行拆分为多个 HTML 表格。`,
|
||||
autoKeywords: '自动关键词提取',
|
||||
|
||||
@ -12,7 +12,7 @@ export const useGetPageTitle = (): string => {
|
||||
[ProfileSettingRouteKey.Api]: 'Api',
|
||||
[ProfileSettingRouteKey.Team]: 'Team management',
|
||||
[ProfileSettingRouteKey.Prompt]: 'Prompt management',
|
||||
[ProfileSettingRouteKey.Chunk]: 'Chunk method',
|
||||
[ProfileSettingRouteKey.Chunk]: 'Chunking method',
|
||||
[ProfileSettingRouteKey.Logout]: 'Logout',
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user