Merge branch 'main' into feat/rag-pipeline

2026-05-05 01:48:04 +08:00 · 2025-06-23 13:59:05 +08:00
parent 3899211c41 ea68c92bbb
commit b9f59e3a75
106 changed files with 5241 additions and 2860 deletions
--- a/web/app/components/datasets/create/step-two/index.tsx
+++ b/web/app/components/datasets/create/step-two/index.tsx
@ -162,7 +162,9 @@ const StepTwo = ({

  const isInCreatePage = !datasetId || (datasetId && !currentDataset?.data_source_type)
  const dataSourceType = isInCreatePage ? inCreatePageDataSourceType : currentDataset?.data_source_type
-  const [segmentationType, setSegmentationType] = useState<ProcessMode>(ProcessMode.general)
+  const [segmentationType, setSegmentationType] = useState<ProcessMode>(
+    currentDataset?.doc_form === ChunkingMode.parentChild ? ProcessMode.parentChild : ProcessMode.general,
+  )
  const [segmentIdentifier, doSetSegmentIdentifier] = useState(DEFAULT_SEGMENT_IDENTIFIER)
  const setSegmentIdentifier = useCallback((value: string, canEmpty?: boolean) => {
    doSetSegmentIdentifier(value ? escape(value) : (canEmpty ? '' : DEFAULT_SEGMENT_IDENTIFIER))
@ -208,7 +210,14 @@ const StepTwo = ({
    }
    if (value === ChunkingMode.parentChild && indexType === IndexingType.ECONOMICAL)
      setIndexType(IndexingType.QUALIFIED)
+
    setDocForm(value)
+
+    if (value === ChunkingMode.parentChild)
+      setSegmentationType(ProcessMode.parentChild)
+    else
+      setSegmentationType(ProcessMode.general)
+
    // eslint-disable-next-line ts/no-use-before-define
    currentEstimateMutation.reset()
  }
@ -504,6 +513,20 @@ const StepTwo = ({
      setOverlap(overlap!)
      setRules(rules.pre_processing_rules)
      setDefaultConfig(rules)
+
+      if (documentDetail.dataset_process_rule.mode === 'hierarchical') {
+        setParentChildConfig({
+          chunkForContext: rules.parent_mode || 'paragraph',
+          parent: {
+            delimiter: escape(rules.segmentation.separator),
+            maxLength: rules.segmentation.max_tokens,
+          },
+          child: {
+            delimiter: escape(rules.subchunk_segmentation.separator),
+            maxLength: rules.subchunk_segmentation.max_tokens,
+          },
+        })
+      }
    }
  }

@ -966,8 +989,8 @@ const StepTwo = ({
                <div className='system-md-semibold mb-0.5 text-text-secondary'>{t('datasetSettings.form.retrievalSetting.title')}</div>
                <div className='body-xs-regular text-text-tertiary'>
                  <a target='_blank' rel='noopener noreferrer'
-                     href={docLink('/guides/knowledge-base/create-knowledge-and-upload-documents')}
-                     className='text-text-accent'>{t('datasetSettings.form.retrievalSetting.learnMore')}</a>
+                    href={docLink('/guides/knowledge-base/create-knowledge-and-upload-documents')}
+                    className='text-text-accent'>{t('datasetSettings.form.retrievalSetting.learnMore')}</a>
                  {t('datasetSettings.form.retrievalSetting.longDescription')}
                </div>
              </div>
@ -1131,7 +1154,7 @@ const StepTwo = ({
                      const indexForLabel = index + 1
                      return (
                        <PreviewSlice
-                          key={child}
+                          key={`C-${indexForLabel}-${child}`}
                          label={`C-${indexForLabel}`}
                          text={child}
                          tooltip={`Child-chunk-${indexForLabel} · ${child.length} Characters`}
--- a/web/app/components/datasets/list/template/template.en.mdx
+++ b/web/app/components/datasets/list/template/template.en.mdx
@ -1124,6 +1124,63 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi

 <hr className='ml-0 mr-0' />

+<Heading
+  url='/datasets/{dataset_id}/documents/status/{action}'
+  method='PATCH'
+  title='Update Document Status'
+  name='#batch_document_status'
+/>
+<Row>
+  <Col>
+    ### Path
+    <Properties>
+      <Property name='dataset_id' type='string' key='dataset_id'>
+        Knowledge ID
+      </Property>
+      <Property name='action' type='string' key='action'>
+        - `enable` - Enable document
+        - `disable` - Disable document
+        - `archive` - Archive document
+        - `un_archive` - Unarchive document
+      </Property>
+    </Properties>
+
+    ### Request Body
+    <Properties>
+      <Property name='document_ids' type='array[string]' key='document_ids'>
+        List of document IDs
+      </Property>
+    </Properties>
+  </Col>
+  <Col sticky>
+    <CodeGroup
+      title="Request"
+      tag="PATCH"
+      label="/datasets/{dataset_id}/documents/status/{action}"
+      targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{\n    "document_ids": ["doc-id-1", "doc-id-2"]\n}'`}
+    >
+    ```bash {{ title: 'cURL' }}
+    curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \
+    --header 'Authorization: Bearer {api_key}' \
+    --header 'Content-Type: application/json' \
+    --data-raw '{
+        "document_ids": ["doc-id-1", "doc-id-2"]
+    }'
+    ```
+    </CodeGroup>
+
+    <CodeGroup title="Response">
+    ```json {{ title: 'Response' }}
+    {
+      "result": "success"
+    }
+    ```
+    </CodeGroup>
+  </Col>
+</Row>
+
+<hr className='ml-0 mr-0' />
+
 <Heading
  url='/datasets/{dataset_id}/documents/{document_id}/segments'
  method='POST'
--- a/web/app/components/datasets/list/template/template.ja.mdx
+++ b/web/app/components/datasets/list/template/template.ja.mdx
@ -881,6 +881,63 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi

 <hr className='ml-0 mr-0' />

+<Heading
+  url='/datasets/{dataset_id}/documents/status/{action}'
+  method='PATCH'
+  title='ドキュメントステータスの更新'
+  name='#batch_document_status'
+/>
+<Row>
+  <Col>
+    ### パス
+    <Properties>
+      <Property name='dataset_id' type='string' key='dataset_id'>
+        ナレッジ ID
+      </Property>
+      <Property name='action' type='string' key='action'>
+        - `enable` - ドキュメントを有効化
+        - `disable` - ドキュメントを無効化
+        - `archive` - ドキュメントをアーカイブ
+        - `un_archive` - ドキュメントのアーカイブを解除
+      </Property>
+    </Properties>
+
+    ### リクエストボディ
+    <Properties>
+      <Property name='document_ids' type='array[string]' key='document_ids'>
+        ドキュメントIDのリスト
+      </Property>
+    </Properties>
+  </Col>
+  <Col sticky>
+    <CodeGroup
+      title="リクエスト"
+      tag="PATCH"
+      label="/datasets/{dataset_id}/documents/status/{action}"
+      targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{\n    "document_ids": ["doc-id-1", "doc-id-2"]\n}'`}
+    >
+    ```bash {{ title: 'cURL' }}
+    curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \
+    --header 'Authorization: Bearer {api_key}' \
+    --header 'Content-Type: application/json' \
+    --data-raw '{
+        "document_ids": ["doc-id-1", "doc-id-2"]
+    }'
+    ```
+    </CodeGroup>
+
+    <CodeGroup title="レスポンス">
+    ```json {{ title: 'Response' }}
+    {
+      "result": "success"
+    }
+    ```
+    </CodeGroup>
+  </Col>
+</Row>
+
+<hr className='ml-0 mr-0' />
+
 <Heading
  url='/datasets/{dataset_id}/documents/{document_id}/segments'
  method='POST'
@ -2413,3 +2470,4 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
  </tbody>
 </table>
 <div className="pb-4" />
+
--- a/web/app/components/datasets/list/template/template.zh.mdx
+++ b/web/app/components/datasets/list/template/template.zh.mdx
@ -1131,6 +1131,63 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi

 <hr className='ml-0 mr-0' />

+<Heading
+  url='/datasets/{dataset_id}/documents/status/{action}'
+  method='PATCH'
+  title='更新文档状态'
+  name='#batch_document_status'
+/>
+<Row>
+  <Col>
+    ### Path
+    <Properties>
+      <Property name='dataset_id' type='string' key='dataset_id'>
+        知识库 ID
+      </Property>
+      <Property name='action' type='string' key='action'>
+        - `enable` - 启用文档
+        - `disable` - 禁用文档
+        - `archive` - 归档文档
+        - `un_archive` - 取消归档文档
+      </Property>
+    </Properties>
+
+    ### Request Body
+    <Properties>
+      <Property name='document_ids' type='array[string]' key='document_ids'>
+        文档ID列表
+      </Property>
+    </Properties>
+  </Col>
+  <Col sticky>
+    <CodeGroup
+      title="Request"
+      tag="PATCH"
+      label="/datasets/{dataset_id}/documents/status/{action}"
+      targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{\n    "document_ids": ["doc-id-1", "doc-id-2"]\n}'`}
+    >
+    ```bash {{ title: 'cURL' }}
+    curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/status/{action}' \
+    --header 'Authorization: Bearer {api_key}' \
+    --header 'Content-Type: application/json' \
+    --data-raw '{
+        "document_ids": ["doc-id-1", "doc-id-2"]
+    }'
+    ```
+    </CodeGroup>
+
+    <CodeGroup title="Response">
+    ```json {{ title: 'Response' }}
+    {
+      "result": "success"
+    }
+    ```
+    </CodeGroup>
+  </Col>
+</Row>
+
+<hr className='ml-0 mr-0' />
+
 <Heading
  url='/datasets/{dataset_id}/documents/{document_id}/segments'
  method='POST'