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/hooks/use-api-access-url.ts

@@ -0,0 +1,16 @@
+import { useMemo } from 'react'
+import { useGetLanguage } from '@/context/i18n'
+
+export const useDatasetApiAccessUrl = () => {
+  const locale = useGetLanguage()
+
+  const apiReferenceUrl = useMemo(() => {
+    if (locale === 'zh_Hans')
+      return 'https://docs.dify.ai/api-reference/%E6%95%B0%E6%8D%AE%E9%9B%86'
+    if (locale === 'ja_JP')
+      return 'https://docs.dify.ai/api-reference/%E3%83%87%E3%83%BC%E3%82%BF%E3%82%BB%E3%83%83%E3%83%88'
+    return 'https://docs.dify.ai/api-reference/datasets'
+  }, [locale])
+
+  return apiReferenceUrl
+}

web/hooks/use-metadata.ts

@@ -1,7 +1,7 @@
 'use client'
 import { useTranslation } from 'react-i18next'
 import { formatFileSize, formatNumber, formatTime } from '@/utils/format'
-import { type DocType, ProcessMode } from '@/models/datasets'
+import { ChunkingMode, type DocType } from '@/models/datasets'
 import useTimestamp from '@/hooks/use-timestamp'
 
 export type inputType = 'input' | 'select' | 'textarea'
@@ -248,9 +248,17 @@ export const useMetadataMap = (): MetadataMap => {
       text: t('datasetDocuments.metadata.type.technicalParameters'),
       allowEdit: false,
       subFieldsMap: {
-        'dataset_process_rule.mode': {
+        'doc_form': {
           label: t(`${fieldPrefix}.technicalParameters.segmentSpecification`),
-          render: value => value === ProcessMode.general ? (t('datasetDocuments.embedding.custom') as string) : (t('datasetDocuments.embedding.hierarchical') as string),
+          render: (value) => {
+            if (value === ChunkingMode.text)
+              return t('dataset.chunkingMode.general')
+            if (value === ChunkingMode.qa)
+              return t('dataset.chunkingMode.qa')
+            if (value === ChunkingMode.parentChild)
+              return t('dataset.chunkingMode.parentChild')
+            return '--'
+          },
         },
         'dataset_process_rule.rules.segmentation.max_tokens': {
           label: t(`${fieldPrefix}.technicalParameters.segmentLength`),