Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

fix: Updated the pipeline tabs to show consistent labels. (#19933)

YanZhang274779d74a67
diff --git a/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json b/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
index f80cc21ee3..ccb2f9b699 100644
--- a/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
+++ b/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
@@ -261,7 +261,7 @@
}
},
"label": "OneChunker",
- "name": "OneChunker"
+ "name": "Audio Chunker"
},
"id": "OneChunker:BlueSkiesLaugh",
"measured": {
diff --git a/internal/ingestion/pipeline/template/ingestion_pipeline_email.json b/internal/ingestion/pipeline/template/ingestion_pipeline_email.json
index 8fdc434844..6941c3958f 100644
--- a/internal/ingestion/pipeline/template/ingestion_pipeline_email.json
+++ b/internal/ingestion/pipeline/template/ingestion_pipeline_email.json
@@ -298,7 +298,7 @@
"overlapped_percent": 0
},
"label": "TokenChunker",
- "name": "Token Chunker"
+ "name": "Email Chunker"
},
"id": "TokenChunker:WarmBreadSmells",
"measured": {
diff --git a/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json b/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
index 86542a91a9..bcba6f733b 100644
--- a/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
+++ b/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
@@ -283,7 +283,7 @@
}
},
"label": "OneChunker",
- "name": "OneChunker"
+ "name": "Picture Chunker"
},
"id": "OneChunker:BrightColorsGlow",
"measured": {
diff --git a/web/src/locales/en.ts b/web/src/locales/en.ts
index 1bf3effbbe..68f0c17a05 100644
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@@ -738,7 +738,7 @@ Example: A 1 KB message with 1024-dim embedding uses ~9 KB. The 5 MB default lim
editLinkDataPipeline: 'Edit ingestion pipeline',
linkPipelineSetTip: 'Manage ingestion pipeline linkage with this dataset',
default: 'Default',
- dataPipeline: 'Switch or configure ingestion pipeline.',
+ dataPipeline: 'Select or switch the parsing mode',
linkDataPipeline: 'Link ingestion pipeline',
enableAutoGenerate: 'Enable auto generate',
teamPlaceholder: 'Please select a team.',
@@ -1080,18 +1080,18 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
knowledgeBasesPlaceholder: 'Select value',
knowledgeBasesMessage: 'Please select',
datasetUnavailable:
- 'The selected knowledge base is unavailable (deleted or has no chunks), please re-select',
+ 'The selected dataset is unavailable (deleted or has no chunks), please re-select',
knowledgeBasesTip:
'Select the datasets to associate with this chat assistant. An empty dataset will not appear in the dropdown list.',
system: 'System prompt',
- systemPlaceholder: `You are an intelligent assistant. Your primary function is to answer questions based strictly on the provided knowledge base.
+ systemPlaceholder: `You are an intelligent assistant. Your primary function is to answer questions based strictly on the provided dataset.
**Essential Rules:**
- Your answer must be derived **solely** from this dataset: {knowledge}.
- **When information is available**: Summarize the content to give a detailed answer.
- - **When information is unavailable**: Your response must contain this exact sentence: "The answer you are looking for is not found in the knowledge base!"
+ - **When information is unavailable**: Your response must contain this exact sentence: "The answer you are looking for is not found in the dataset!"
- **Always consider** the entire conversation history.`,
- systemInitialValue: `You are an intelligent assistant. Your primary function is to answer questions based strictly on the provided knowledge base.
+ systemInitialValue: `You are an intelligent assistant. Your primary function is to answer questions based strictly on the provided dataset.
**Essential Rules:**
- Your answer must be derived **solely** from this dataset: \`{knowledge}\`.
@@ -1617,7 +1617,7 @@ Example: Virtual Hosted Style`,
timeStarted: 'Time started',
log: 'Log',
rssDescription:
- 'Connect to a public RSS or Atom feed and sync feed entries into your knowledge base.',
+ 'Connect to a public RSS or Atom feed and sync feed entries into your dataset.',
confluenceDescription:
'Integrate your Confluence workspace to search documentation.',
s3Description:
@@ -2461,7 +2461,7 @@ Example: Virtual Hosted Style`,
jsonPreview: 'JSON preview',
processFlow: 'Process flow',
processFlowComingSoon: 'Process flow preview coming soon',
- compilationTitleSuffix: "' dataset",
+ compilationTitleSuffix: ' dataset',
llmWiki: 'Wiki',
skills: 'To Skills',
navTree: 'Tree/PageIndex',
@@ -3503,7 +3503,7 @@ This process aggregates variables from multiple branches into a single variable
retrievalMemoryMissing:
'Cannot save: "{{name}}" has no memories selected. Please choose them first',
retrievalTemplateDatasetHint:
- 'This template contains {{num}} dataset retrieval step(s) without a bound knowledge base. Pick one below and it will be applied to all of them; you can still adjust each retrieval on the canvas after creation.',
+ 'This template contains {{num}} retrieval step(s) without a bound dataset. Pick one below and it will be applied to all of them; you can still adjust each retrieval on the canvas after creation.',
retrievalTemplateMemoryHint:
'This template contains {{num}} retrieval step(s) without bound memories. Pick memories below and they will be applied to all of them; you can still adjust each retrieval on the canvas after creation.',
retrievalDatasetRequired: 'Please select a knowledge base first',
diff --git a/web/src/locales/zh.ts b/web/src/locales/zh.ts
index c96cf89002..ffeccc1faf 100644
--- a/web/src/locales/zh.ts
+++ b/web/src/locales/zh.ts
@@ -98,7 +98,7 @@ export default {
title: 'A leading RAG engine for LLM context',
start: '立即开始',
description:
- '免费注册以探索顶级 RAG 技术。 创建知识库和人工智能来增强您的业务',
+ '免费注册以探索顶级 RAG 技术。 创建知识库和人工智能来增强业务',
review: '来自 500 多条评论',
},
header: {
@@ -130,7 +130,7 @@ export default {
spaceName: 'Skills 空间名称',
spaceNamePlaceholder: '例如:my-space',
spaceNameRequired: '请输入空间名称',
- noSpaces: '暂无 Skills 空间,创建您的第一个!',
+ noSpaces: '暂无 Skills 空间,创建第一个!',
enterSpace: '进入',
spaceCreated: 'Skills 空间创建成功',
spaceDeleted: 'Skills 空间删除成功',
@@ -146,7 +146,7 @@ export default {
skillExists: '同名 Skills 已存在,请先删除或使用其他名称',
uploadSkill: '上传 Skills',
searchPlaceholder: '搜索 Skills...',
- noSkills: '暂无 Skills,上传您的第一个 Skill',
+ noSkills: '暂无 Skills,上传第一个 Skill',
noSearchResults: '没有找到匹配的 Skill',
filesCount: '{{count}} 个文件',
foldersCount: '{{count}} 个文件夹',
@@ -318,7 +318,7 @@ export default {
},
config: {
titleDescription: '在这里更新您的记忆配置,特别是大语言模型和提示词。',
- descriptionPlaceholder: '描述你的记忆',
+ descriptionPlaceholder: '描述您的记忆',
memorySizeTooltip: `记录每条消息的内容 + 其 Embedding(≈ 内容 + 维度 × 8 字节)。
例如:一条带有 1024 维 Embedding 的 1 KB 消息大约使用 9 KB。5 MB 的默认限制大约可容纳 500 条此类消息。`,
avatar: '头像',
@@ -438,9 +438,9 @@ export default {
generateArtifact:
'从配置了知识编译模板的每个文档中编译 Artifact 页面(Entity / Concept / Topic)。每次运行仅处理新添加的 Chunk。',
generateToSkills:
- '从该数据集构建分层 Skills 树,并存储生成的 Skills 页面以供搜索和复用。',
+ '从该知识库构建分层 Skills 树,并存储生成的 Skills 页面以供搜索和复用。',
processingType: '处理类型',
- dataPipeline: '切换或配置 ingestion pipeline。',
+ dataPipeline: '选择或切换解析方式',
dataPipelineTitle: '数据管道',
operations: '操作',
taskId: '任务ID',
@@ -459,7 +459,7 @@ export default {
completed: '已完成',
datasetLog: '知识库日志',
created: '创建于',
- learnMore: '查看内置解析方法说明',
+ learnMore: '查看内置解析模板说明',
general: '通用',
chunkMethodTab: '切片方法',
testResults: '测试结果',
@@ -510,7 +510,7 @@ export default {
keywordSimilarityWeightTip:
'此项用于设置混合相似度分数中的关键词相似度权重。向量与关键词相似度权重的总和必须等于 1.0。',
testText: '测试文本',
- testTextPlaceholder: '请输入您的问题!',
+ testTextPlaceholder: '请输问题!',
testingLabel: '运行',
similarity: '混合相似度',
termSimilarity: '关键词相似度',
@@ -539,7 +539,7 @@ export default {
layoutRecognizeTip:
'使用视觉模型进行 PDF 布局分析,以更好地识别文档结构,找到标题、文本块、图像和表格的位置。 如果选择 Naive 选项,则只能获取 PDF 的纯文本。请注意该功能只适用于 PDF 文档,对其他文档不生效。欲了解更多信息,请参阅 https://ragflow.io/docs/dataset_configuration#document-parsing-configuration。',
taskPageSize: '任务页面大小',
- taskPageSizeMessage: '请输入您的任务页面大小!',
+ taskPageSizeMessage: '请输入任务页面大小!',
taskPageSizeTip: `如果使用布局识别,PDF 文件将被分成连续的组。 布局分析将在组之间并行执行,以提高处理速度。 “任务页面大小”决定组的大小。 页面大小越大,将页面之间的连续文本分割成不同块的机会就越低。`,
addPage: '新增页面',
greaterThan: '当前值必须大于起始值!',
@@ -575,7 +575,7 @@ export default {
autoKeywordsTip: `自动为每个文本块中提取 N 个关键词,用以提升查询精度。请注意:该功能采用在“配置”中指定的索引模型提取关键词,因此也会产生更多 Token 消耗。另外,你也可以手动更新生成的关键词。详情请见 https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration。`,
autoQuestions: '自动问题提取数',
autoQuestionsTip: `利用在“配置”中指定的索引模型 对知识库的每个文本块提取 N 个问题以提高其排名得分。请注意,开启后将消耗额外的 Token。您可以在块列表中查看、编辑结果。如果自动问题提取发生错误,不会妨碍整个分块过程,只会将空结果添加到原始文本块。详情请见 https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration。`,
- autoTags: '自动标签提取',
+ autoTags: '自动标签提取数',
redo: '是否清空已有 {{chunkNum}}个 Chunk?',
setMetaData: '设置元数据',
pleaseInputJson: '请输入JSON',
@@ -688,7 +688,7 @@ export default {
builtIn: '内置解析模板',
noConfigChunkerHint:
'内置的 {{name}} 解析器会自动处理分块,因此无需额外配置。',
- titleDescription: '在这里更新您的知识库配置,特别是大语言模型和提示词。',
+ titleDescription: '在这里更新知识库配置,特别是大语言模型和提示词。',
name: '知识库名称',
photo: '知识库图片',
photoTip: '可以上传 4MB 以内的文件',
@@ -728,7 +728,7 @@ export default {
<p>本方法使用语音转文本模型将音频文件转录为文本。</p>`,
email: `<p>支持的文件格式为 <b>EML</b> 和 <b>MSG</b>。</p>
<p>本方法解析电子邮件文件,提取头部字段(如发件人、收件人、抄送、主题和日期)、正文内容以及附件。</p>`,
- knowledgeCompiler: `<p>本 pipeline 先解析文件并分块,然后通过 Knowledge Compiler 组件将分块编译为结构化知识单元(知识图谱、百科、RAPTOR、思维导图或数据集导航)。</p>
+ knowledgeCompiler: `<p>本 pipeline 先解析文件并分块,然后通过 Knowledge Compiler 组件将分块编译为结构化知识单元(知识图谱、百科、RAPTOR、思维导图或知识库导航)。</p>
<p>编译后的知识单元以分块形式合并进分块流输出,适合在分块文档之上构建可检索的知识层。</p>`,
book: `<p>支持的文件格式为<b>DOCX</b>、<b>PDF</b>、<b>TXT</b>。</p><p>
由于一本书很长,并不是所有部分都有用,如果是 PDF,
@@ -943,7 +943,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
chat: {
chatSupport: '聊天支持',
replyInstantly: '我们通常会即时回复',
- typeYourMessage: '输入您的消息...',
+ typeYourMessage: '输入消息...',
messagePlaceholder: '请输入消息...',
exit: '退出',
multipleModels: '多模型',
@@ -1446,7 +1446,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
dataSourceFieldProjectId: '项目 ID',
dataSourceFieldLocation: '位置',
dataSourceFieldServiceAccountJson: '服务账号 JSON',
- dataSourceFieldDatasetId: '数据集 ID',
+ dataSourceFieldDatasetId: '知识库 ID',
dataSourceFieldTableId: '表 ID',
dataSourceFieldMaxBytesBilled: '最大计费字节数',
dataSourceFieldJobTimeout: '作业超时时间(毫秒)',
@@ -1579,11 +1579,11 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
dataSourceAzureSasTokenRequired: '使用 SAS 令牌认证时,SAS 令牌为必填项',
dataSourceAzureContainerNameRequired: '在此认证模式下,容器名称为必填项',
dataSourceBigqueryDatasetIdRequired:
- '未使用自定义 SQL 查询时,数据集 ID 为必填项',
+ '未使用自定义 SQL 查询时,知识库 ID 为必填项',
dataSourceBigqueryTableIdRequired:
'未使用自定义 SQL 查询时,表 ID 为必填项',
dataSourceBigqueryQueryRequired:
- '请提供 SQL 查询,或同时提供数据集 ID 和表 ID',
+ '请提供 SQL 查询,或同时提供知识库 ID 和表 ID',
dataSourceSalesforceInstanceUrlInvalid:
'必须为合法的 Salesforce 域名 (https://...salesforce.com)',
dataSourceSalesforceApiVersionInvalid: 'API 版本格式必须如 v59.0',
@@ -2072,7 +2072,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
jsonPreview: 'JSON 预览',
processFlow: '流程视图',
processFlowComingSoon: '流程视图预览即将到来',
- compilationTitleSuffix: '的数据集',
+ compilationTitleSuffix: '的知识库',
llmWiki: 'Wiki',
skills: 'To Skills',
navTree: 'Tree/PageIndex',
@@ -2091,7 +2091,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
sourceDocuments: '来源文档',
clearWikiTitle: '清空 Wiki',
clearWikiDescription:
- '确定要清空该数据集下的所有 Wiki 页面吗?此操作无法撤销。',
+ '确定要清空该知识库下的所有 Wiki 页面吗?此操作无法撤销。',
update: '更新',
updateTooltip:
'发现 {{newlyUploaded}} 个新文档,{{removed}} 个已移除文档,{{changed}} 个已变更文档。点击编译并合并到当前 Wiki。',
@@ -3049,7 +3049,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
retrievalDatasetMissing: '无法保存:“{{name}}” 未选择知识库,请先选择',
retrievalMemoryMissing: '无法保存:“{{name}}” 未选择记忆,请先选择',
retrievalTemplateDatasetHint:
- '该模板包含 {{num}} 处未绑定知识库的数据集检索,请在下方选择一个知识库,将应用到全部检索;创建后仍可在画布中逐处调整。',
+ '该模板包含 {{num}} 处未绑定知识库的检索,请在下方选择一个知识库,将应用到全部检索;创建后仍可在画布中逐处调整。',
retrievalTemplateMemoryHint:
'该模板包含 {{num}} 处未绑定记忆的检索,请在下方选择记忆,将应用到全部检索;创建后仍可在画布中逐处调整。',
retrievalDatasetRequired: '请先选择知识库',