youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-24 04:45:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

update knowledge base api (#20426)

Browse Source
This commit is contained in:
Dongyu Li
2025-05-30 14:45:30 +08:00
committed by GitHub
parent 55371e5abf
commit 1ea4459d9f
6 changed files with 397 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
web/app/(commonLayout)/datasets/template/template.en.mdx
View File

@ -1298,6 +1298,76 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
method='GET'
title='Get a Chunk Details in a Document'
name='#view_document_chunk'
/>
<Row>
<Col>
Get details of a specific document segment in the specified knowledge base
### Path
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge Base ID
</Property>
<Property name='document_id' type='string' key='document_id'>
Document ID
</Property>
<Property name='segment_id' type='string' key='segment_id'>
Segment ID
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup
title="Request"
tag="GET"
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
>
```bash {{ title: 'cURL' }}
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
--header 'Authorization: Bearer {api_key}'
```
</CodeGroup>
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"data": {
"id": "chunk_id",
"position": 2,
"document_id": "document_id",
"content": "Segment content text",
"sign_content": "Signature content text",
"answer": "Answer content (if in Q&A mode)",
"word_count": 470,
"tokens": 382,
"keywords": ["keyword1", "keyword2"],
"index_node_id": "index_node_id",
"index_node_hash": "index_node_hash",
"hit_count": 0,
"enabled": true,
"status": "completed",
"created_by": "creator_id",
"created_at": creation_timestamp,
"updated_at": update_timestamp,
"indexing_at": indexing_timestamp,
"completed_at": completion_timestamp,
"error": null,
"child_chunks": []
},
"doc_form": "text_model"
}
```
</CodeGroup>
</Col>
</Row>
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
method='DELETE'
@ -1771,20 +1841,45 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
Query keyword
</Property>
<Property name='retrieval_model' type='object' key='retrieval_model'>
Retrieval model (optional, if not filled, it will be recalled according to the default method)
- <code>search_method</code> (text) Search method: One of the following four keywords is required
- <code>keyword_search</code> Keyword search
- <code>semantic_search</code> Semantic search
- <code>full_text_search</code> Full-text search
- <code>hybrid_search</code> Hybrid search
- <code>reranking_enable</code> (bool) Whether to enable reranking, required if the search mode is semantic_search or hybrid_search (optional)
- <code>reranking_mode</code> (object) Rerank model configuration, required if reranking is enabled
- <code>reranking_provider_name</code> (string) Rerank model provider
- <code>reranking_model_name</code> (string) Rerank model name
- <code>weights</code> (float) Semantic search weight setting in hybrid search mode
- <code>top_k</code> (integer) Number of results to return (optional)
- <code>score_threshold_enabled</code> (bool) Whether to enable score threshold
- <code>score_threshold</code> (float) Score threshold
Retrieval parameters (optional, if not filled, it will be recalled according to the default method)
- <code>search_method</code> (text) Search method: One of the following four keywords is required
- <code>keyword_search</code> Keyword search
- <code>semantic_search</code> Semantic search
- <code>full_text_search</code> Full-text search
- <code>hybrid_search</code> Hybrid search
- <code>reranking_enable</code> (bool) Whether to enable reranking, required if the search mode is semantic_search or hybrid_search (optional)
- <code>reranking_mode</code> (object) Rerank model configuration, required if reranking is enabled
- <code>reranking_provider_name</code> (string) Rerank model provider
- <code>reranking_model_name</code> (string) Rerank model name
- <code>weights</code> (float) Semantic search weight setting in hybrid search mode
- <code>top_k</code> (integer) Number of results to return (optional)
- <code>score_threshold_enabled</code> (bool) Whether to enable score threshold
- <code>score_threshold</code> (float) Score threshold
- <code>metadata_filtering_conditions</code> (object) Metadata filtering conditions
- <code>logical_operator</code> (string) Logical operator: <code>and</code> | <code>or</code>
- <code>conditions</code> (array[object]) Conditions list
- <code>name</code> (string) Metadata field name
- <code>comparison_operator</code> (string) Comparison operator, allowed values:
- String comparison:
- <code>contains</code>: Contains
- <code>not contains</code>: Does not contain
- <code>start with</code>: Starts with
- <code>end with</code>: Ends with
- <code>is</code>: Equals
- <code>is not</code>: Does not equal
- <code>empty</code>: Is empty
- <code>not empty</code>: Is not empty
- Numeric comparison:
- <code>=</code>: Equals
- <code>≠</code>: Does not equal
- <code>></code>: Greater than
- <code>< </code>: Less than
- <code>≥</code>: Greater than or equal
- <code>≤</code>: Less than or equal
- Time comparison:
- <code>before</code>: Before
- <code>after</code>: After
- <code>value</code> (string|number|null) Comparison value
</Property>
<Property name='external_retrieval_model' type='object' key='external_retrieval_model'>
Unused field
@ -1809,7 +1904,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
"weights": null,
"top_k": 1,
"score_threshold_enabled": false,
"score_threshold": null
"score_threshold": null,
"metadata_filtering_conditions": {
"logical_operator": "and",
"conditions": [
{
"name": "document_name",
"comparison_operator": "contains",
"value": "test"
}
]
}
}
}'`}
>
@ -2089,9 +2194,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
label="/datasets/{dataset_id}/documents/metadata"
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/metadata' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'\\\n--data-raw '{"operation_data": [{"document_id": "document_id", "metadata_list": [{"id": "id", "value": "value", "name": "name"}]}]}'`}
>
```bash {{ title: 'cURL' }}
```
</CodeGroup>
```bash {{ title: 'cURL' }} </CodeGroup>
</Col>
</Row>

135
web/app/(commonLayout)/datasets/template/template.ja.mdx
View File

@ -1057,6 +1057,75 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<Heading
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
method='GET'
title='ドキュメントセグメントの詳細を表示'
name='#view_document_segment'
/>
<Row>
<Col>
指定されたナレッジベース内の特定のドキュメントセグメントの詳細を表示します
### パス
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
ナレッジベースID
</Property>
<Property name='document_id' type='string' key='document_id'>
ドキュメントID
</Property>
<Property name='segment_id' type='string' key='segment_id'>
セグメントID
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup
title="リクエスト"
tag="GET"
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
>
```bash {{ title: 'cURL' }}
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
--header 'Authorization: Bearer {api_key}'
```
</CodeGroup>
<CodeGroup title="レスポンス">
```json {{ title: 'Response' }}
{
"data": {
"id": "セグメントID",
"position": 2,
"document_id": "ドキュメントID",
"content": "セグメント内容テキスト",
"sign_content": "署名内容テキスト",
"answer": "回答内容(Q&Aモードの場合)",
"word_count": 470,
"tokens": 382,
"keywords": ["キーワード1", "キーワード2"],
"index_node_id": "インデックスノードID",
"index_node_hash": "インデックスノードハッシュ",
"hit_count": 0,
"enabled": true,
"status": "completed",
"created_by": "作成者ID",
"created_at": 作成タイムスタンプ,
"updated_at": 更新タイムスタンプ,
"indexing_at": インデックス作成タイムスタンプ,
"completed_at": 完了タイムスタンプ,
"error": null,
"child_chunks": []
},
"doc_form": "text_model"
}
```
</CodeGroup>
</Col>
</Row>
<hr className='ml-0 mr-0' />
<Heading
method='DELETE'
title='ドキュメント内のチャンクを削除'
name='#delete_segment'
@ -1100,7 +1169,6 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
method='POST'
title='ドキュメント内のチャンクを更新'
name='#update_segment'
@ -1528,20 +1596,45 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
クエリキーワード
</Property>
<Property name='retrieval_model' type='object' key='retrieval_model'>
検索モデル (オプション、入力されない場合はデフォルトの方法でリコールされます)
- <code>search_method</code> (text) 検索方法: 以下の 4 つのキーワードのいずれかが必要です
- <code>keyword_search</code> キーワード検索
- <code>semantic_search</code> セマンティック検索
- <code>full_text_search</code> 全文検索
- <code>hybrid_search</code> ハイブリッド検索
- <code>reranking_enable</code> (bool) 再ランキングを有効にするかどうか、検索モードが semantic_search または hybrid_search の場合に必須 (オプション)
- <code>reranking_mode</code> (object) 再ランキングモデル構成、再ランキングが有効な場合に必須
- <code>reranking_provider_name</code> (string) 再ランキングモデルプロバイダー
- <code>reranking_model_name</code> (string) 再ランキングモデル名
- <code>weights</code> (float) ハイブリッド検索モードでのセマンティック検索の重み設定
- <code>top_k</code> (integer) 返される結果の数 (オプション)
- <code>score_threshold_enabled</code> (bool) スコア閾値を有効にするかどうか
- <code>score_threshold</code> (float) スコア閾値
検索パラメータ（オプション、入力されない場合はデフォルトの方法でリコールされます）
- <code>search_method</code> (text) 検索方法: 以下の4つのキーワードのいずれかが必要です
- <code>keyword_search</code> キーワード検索
- <code>semantic_search</code> セマンティック検索
- <code>full_text_search</code> 全文検索
- <code>hybrid_search</code> ハイブリッド検索
- <code>reranking_enable</code> (bool) 再ランキングを有効にするかどうか、検索モードがsemantic_searchまたはhybrid_searchの場合に必須（オプション）
- <code>reranking_mode</code> (object) 再ランキングモデル構成、再ランキングが有効な場合に必須
- <code>reranking_provider_name</code> (string) 再ランキングモデルプロバイダー
- <code>reranking_model_name</code> (string) 再ランキングモデル名
- <code>weights</code> (float) ハイブリッド検索モードでのセマンティック検索の重み設定
- <code>top_k</code> (integer) 返される結果の数（オプション）
- <code>score_threshold_enabled</code> (bool) スコア閾値を有効にするかどうか
- <code>score_threshold</code> (float) スコア閾値
- <code>metadata_filtering_conditions</code> (object) メタデータフィルタリング条件
- <code>logical_operator</code> (string) 論理演算子: <code>and</code> | <code>or</code>
- <code>conditions</code> (array[object]) 条件リスト
- <code>name</code> (string) メタデータフィールド名
- <code>comparison_operator</code> (string) 比較演算子、許可される値:
- 文字列比較:
- <code>contains</code>: 含む
- <code>not contains</code>: 含まない
- <code>start with</code>: で始まる
- <code>end with</code>: で終わる
- <code>is</code>: 等しい
- <code>is not</code>: 等しくない
- <code>empty</code>: 空
- <code>not empty</code>: 空でない
- 数値比較:
- <code>=</code>: 等しい
- <code>≠</code>: 等しくない
- <code>></code>: より大きい
- <code>< </code>: より小さい
- <code>≥</code>: 以上
- <code>≤</code>: 以下
- 時間比較:
- <code>before</code>: より前
- <code>after</code>: より後
- <code>value</code> (string|number|null) 比較値
</Property>
<Property name='external_retrieval_model' type='object' key='external_retrieval_model'>
未使用フィールド
@ -1566,7 +1659,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
"weights": null,
"top_k": 1,
"score_threshold_enabled": false,
"score_threshold": null
"score_threshold": null,
"metadata_filtering_conditions": {
"logical_operator": "and",
"conditions": [
{
"name": "document_name",
"comparison_operator": "contains",
"value": "test"
}
]
}
}
}'`}
>

106
web/app/(commonLayout)/datasets/template/template.zh.mdx
View File

@ -1351,6 +1351,75 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<Heading
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
method='GET'
title='查看文档分段详情'
name='#view_document_segment'
/>
<Row>
<Col>
查看指定知识库中特定文档的分段详情
### Path
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
知识库 ID
</Property>
<Property name='document_id' type='string' key='document_id'>
文档 ID
</Property>
<Property name='segment_id' type='string' key='segment_id'>
分段 ID
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup
title="Request"
tag="GET"
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
>
```bash {{ title: 'cURL' }}
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
--header 'Authorization: Bearer {api_key}'
```
</CodeGroup>
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"data": {
"id": "分段唯一ID",
"position": 2,
"document_id": "所属文档ID",
"content": "分段内容文本",
"sign_content": "签名内容文本",
"answer": "答案内容(如果有)",
"word_count": 470,
"tokens": 382,
"keywords": ["关键词1", "关键词2"],
"index_node_id": "索引节点ID",
"index_node_hash": "索引节点哈希值",
"hit_count": 0,
"enabled": true,
"status": "completed",
"created_by": "创建者ID",
"created_at": 创建时间戳,
"updated_at": 更新时间戳,
"indexing_at": 索引时间戳,
"completed_at": 完成时间戳,
"error": null,
"child_chunks": []
},
"doc_form": "text_model"
}
```
</CodeGroup>
</Col>
</Row>
<hr className='ml-0 mr-0' />
<Heading
method='POST'
title='更新文档分段'
name='#update_segment'
@ -1827,6 +1896,31 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
- <code>top_k</code> (integer) 返回结果数量，非必填
- <code>score_threshold_enabled</code> (bool) 是否开启 score 阈值
- <code>score_threshold</code> (float) Score 阈值
- <code>metadata_filtering_conditions</code> (object) 元数据过滤条件
- <code>logical_operator</code> (string) 逻辑运算符: <code>and</code> | <code>or</code>
- <code>conditions</code> (array[object]) 条件列表
- <code>name</code> (string) 元数据字段名
- <code>comparison_operator</code> (string) 比较运算符，可选值:
- 字符串比较:
- <code>contains</code>: 包含
- <code>not contains</code>: 不包含
- <code>start with</code>: 以...开头
- <code>end with</code>: 以...结尾
- <code>is</code>: 等于
- <code>is not</code>: 不等于
- <code>empty</code>: 为空
- <code>not empty</code>: 不为空
- 数值比较:
- <code>=</code>: 等于
- <code>≠</code>: 不等于
- <code>></code>: 大于
- <code> < </code>: 小于
- <code>≥</code>: 大于等于
- <code>≤</code>: 小于等于
- 时间比较:
- <code>before</code>: 早于
- <code>after</code>: 晚于
- <code>value</code> (string|number|null) 比较值
</Property>
<Property name='external_retrieval_model' type='object' key='external_retrieval_model'>
未启用字段
@ -1851,7 +1945,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
"weights": null,
"top_k": 1,
"score_threshold_enabled": false,
"score_threshold": null
"score_threshold": null,
"metadata_filtering_conditions": {
"logical_operator": "and",
"conditions": [
{
"name": "document_name",
"comparison_operator": "contains",
"value": "test"
}
]
}
}
}'`}
>