RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
fix: Add tag file format instructions in UI (#21417)
YanZhang1dcb0d7eb5dc
diff --git a/web/src/locales/en.ts b/web/src/locales/en.tsindex 6497f44d9e..3cec98e086 100644--- a/web/src/locales/en.ts+++ b/web/src/locales/en.ts@@ -3408,7 +3408,7 @@ This delimiter is used to split the input text into several text pieces echo ofuserPrompt: 'User prompt',tagFile: 'Tag file',tagFileTip:- 'Automatically extracts up to N relevant tags for each chunk based on the selected tag file to improve retrieval accuracy. Tag extraction may invoke a model and consume additional tokens. If extraction fails, the original chunk will be preserved. For details, see https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration.',+ 'Automatically extracts up to N relevant tags per chunk to improve retrieval accuracy. Supports XLSX, XLS, CSV, and TXT files, with two columns for text and tags. Separate multiple tags with commas. No header required. Tag extraction may consume additional tokens. The original chunk is preserved if extraction fails. For details, see https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration.',addCategory: 'Add category',categoryName: 'Category name',nextStep: 'Next step',diff --git a/web/src/locales/zh.ts b/web/src/locales/zh.tsindex 92e8fbfa3f..8fb07a75b4 100644--- a/web/src/locales/zh.ts+++ b/web/src/locales/zh.ts@@ -2999,7 +2999,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 RuserPrompt: '用户提示词',tagFile: '标签文件',tagFileTip:- '根据所选标签文件,为每个文本块自动提取最多 N 个相关标签,以提高检索准确性。标签提取可能调用模型并产生额外的 Token 消耗。如果提取失败,原始文本块仍会保留。详情请见 https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration。',+ '根据所选标签文件,为每个文本块自动提取最多 N 个相关标签,以提高检索准确性。标签文件支持 XLSX、XLS、CSV、TXT 格式,每行包含文本和标签两列,多个标签用英文逗号分隔,无需表头。标签提取可能产生额外的 Token 消耗。提取失败时,原始文本块仍会保留。详情请见 https://ragflow.io/docs/dataset_configuration#content-enhancement-configuration。',prompt: '提示词',promptMessage: '提示词是必填项',promptTip: