feat: knowledge pipeline (#25360)

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
Co-authored-by: lyzno1 <yuanyouhuilyz@gmail.com>
Co-authored-by: quicksand <quicksandzn@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: lyzno1 <92089059+lyzno1@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Hanqing Zhao <sherry9277@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry <xh001x@hotmail.com>

web/i18n/en-US/dataset-creation.ts

@@ -38,7 +38,7 @@ const translation = {
       button: 'Drag and drop file or folder, or',
       buttonSingleFile: 'Drag and drop file, or',
       browse: 'Browse',
-      tip: 'Supports {{supportTypes}}. Max {{size}}MB each.',
+      tip: 'Supports {{supportTypes}}. Max {{batchCount}} in a batch and {{size}} MB each.',
       validation: {
         typeError: 'File type not supported',
         size: 'File too large. Maximum is {{size}}MB',
@@ -79,6 +79,7 @@ const translation = {
       configureWatercrawl: 'Configure Watercrawl',
       configureJinaReader: 'Configure Jina Reader',
       run: 'Run',
+      running: 'Running',
       firecrawlTitle: 'Extract web content with 🔥Firecrawl',
       firecrawlDoc: 'Firecrawl docs',
       watercrawlTitle: 'Extract web content with Watercrawl',
@@ -121,6 +122,7 @@ const translation = {
     paragraphTip: 'This mode splits the text in to paragraphs based on delimiters and the maximum chunk length, using the split text as the parent chunk for retrieval.',
     fullDoc: 'Full Doc',
     fullDocTip: 'The entire document is used as the parent chunk and retrieved directly. Please note that for performance reasons, text exceeding 10000 tokens will be automatically truncated.',
+    qaTip: 'When using structured Q&A data, you can create documents that pair questions with answers. These documents are indexed based on the question portion, allowing the system to retrieve relevant answers based on query similarity.',
     separator: 'Delimiter',
     separatorTip: 'A delimiter is the character used to separate text. \\n\\n and \\n are commonly used delimiters for separating paragraphs and lines. Combined with commas (\\n\\n,\\n), paragraphs will be segmented by lines when exceeding the maximum chunk length. You can also use special delimiters defined by yourself (e.g. ***).',
     separatorPlaceholder: '\\n\\n for paragraphs; \\n for lines',
@@ -199,7 +201,7 @@ const translation = {
     resume: 'Resume processing',
     navTo: 'Go to document',
     sideTipTitle: 'What\'s next',
-    sideTipContent: 'After the document finishes indexing, the Knowledge can be integrated into the application as context, you can find the context setting in the prompt orchestration page. You can also create it as an independent ChatGPT indexing plugin for release.',
+    sideTipContent: 'After finishing document indexing, you can manage and edit documents, run retrieval tests, and modify knowledge settings. Knowledge can then be integrated into your application as context, so make sure to adjust the Retrieval Setting to ensure optimal performance.',
     modelTitle: 'Are you sure to stop embedding?',
     modelContent: 'If you need to resume processing later, you will continue from where you left off.',
     modelButtonConfirm: 'Confirm',