estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add get document detail service api (#21700)

Browse Source 
Co-authored-by: lizb <lizb@sugon.com>
This commit is contained in:
Ganondorf
2025-06-30 22:13:56 +08:00
committed by GitHub
parent 96d27d7087
commit 55a6b330ec
5 changed files with 479 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
web/app/(commonLayout)/datasets/template/template.en.mdx
View File

@@ -1124,6 +1124,129 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}'
method='GET'
title='Get Document Detail'
name='#get-document-detail'
/>
<Row>
<Col>
Get a document's detail.
### Path
- `dataset_id` (string) Dataset ID
- `document_id` (string) Document ID
### Query
- `metadata` (string) Metadata filter, can be `all`, `only`, or `without`. Default is `all`.
### Response
Returns the document's detail.
</Col>
<Col sticky>
### Request Example
<CodeGroup title="Request" tag="GET" label="/datasets/{dataset_id}/documents/{document_id}" targetCode={`curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n-H 'Authorization: Bearer {api_key}'`}>
```bash {{ title: 'cURL' }}
curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
-H 'Authorization: Bearer {api_key}'
```
</CodeGroup>
### Response Example
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"id": "f46ae30c-5c11-471b-96d0-464f5f32a7b2",
"position": 1,
"data_source_type": "upload_file",
"data_source_info": {
"upload_file": {
...
}
},
"dataset_process_rule_id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_process_rule": {
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"document_process_rule": {
"id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_id": "48a0db76-d1a9-46c1-ae35-2baaa919a8a9",
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"name": "xxxx",
"created_from": "web",
"created_by": "17f71940-a7b5-4c77-b60f-2bd645c1ffa0",
"created_at": 1750464191,
"tokens": null,
"indexing_status": "waiting",
"completed_at": null,
"updated_at": 1750464191,
"indexing_latency": null,
"error": null,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"archived": false,
"segment_count": 0,
"average_segment_length": 0,
"hit_count": null,
"display_status": "queuing",
"doc_form": "hierarchical_model",
"doc_language": "Chinese Simplified"
}
```
</CodeGroup>
</Col>
</Row>
___
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/status/{action}'
method='PATCH'

124
web/app/(commonLayout)/datasets/template/template.ja.mdx
View File

@@ -881,6 +881,130 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}'
method='GET'
title='ドキュメントの詳細を取得'
name='#get-document-detail'
/>
<Row>
<Col>
ドキュメントの詳細を取得.
### Path
- `dataset_id` (string) ナレッジベースID
- `document_id` (string) ドキュメントID
### Query
- `metadata` (string) metadataのフィルター条件 `all`、`only`、または`without`。デフォルトは `all`。
### Response
ナレッジベースドキュメントの詳細を返す.
</Col>
<Col sticky>
### Request Example
<CodeGroup title="Request" tag="GET" label="/datasets/{dataset_id}/documents/{document_id}" targetCode={`curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n-H 'Authorization: Bearer {api_key}'`}>
```bash {{ title: 'cURL' }}
curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
-H 'Authorization: Bearer {api_key}'
```
</CodeGroup>
### Response Example
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"id": "f46ae30c-5c11-471b-96d0-464f5f32a7b2",
"position": 1,
"data_source_type": "upload_file",
"data_source_info": {
"upload_file": {
...
}
},
"dataset_process_rule_id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_process_rule": {
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"document_process_rule": {
"id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_id": "48a0db76-d1a9-46c1-ae35-2baaa919a8a9",
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"name": "xxxx",
"created_from": "web",
"created_by": "17f71940-a7b5-4c77-b60f-2bd645c1ffa0",
"created_at": 1750464191,
"tokens": null,
"indexing_status": "waiting",
"completed_at": null,
"updated_at": 1750464191,
"indexing_latency": null,
"error": null,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"archived": false,
"segment_count": 0,
"average_segment_length": 0,
"hit_count": null,
"display_status": "queuing",
"doc_form": "hierarchical_model",
"doc_language": "Chinese Simplified"
}
```
</CodeGroup>
</Col>
</Row>
___
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/status/{action}'
method='PATCH'

124
web/app/(commonLayout)/datasets/template/template.zh.mdx
View File

@@ -1131,6 +1131,130 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/{document_id}'
method='GET'
title='获取文档详情'
name='#get-document-detail'
/>
<Row>
<Col>
获取文档详情.
### Path
- `dataset_id` (string) 知识库 ID
- `document_id` (string) 文档 ID
### Query
- `metadata` (string) metadata 过滤条件 `all`, `only`, 或者 `without`. 默认是 `all`.
### Response
返回知识库文档的详情.
</Col>
<Col sticky>
### Request Example
<CodeGroup title="Request" tag="GET" label="/datasets/{dataset_id}/documents/{document_id}" targetCode={`curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n-H 'Authorization: Bearer {api_key}'`}>
```bash {{ title: 'cURL' }}
curl -X GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
-H 'Authorization: Bearer {api_key}'
```
</CodeGroup>
### Response Example
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"id": "f46ae30c-5c11-471b-96d0-464f5f32a7b2",
"position": 1,
"data_source_type": "upload_file",
"data_source_info": {
"upload_file": {
...
}
},
"dataset_process_rule_id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_process_rule": {
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"document_process_rule": {
"id": "24b99906-845e-499f-9e3c-d5565dd6962c",
"dataset_id": "48a0db76-d1a9-46c1-ae35-2baaa919a8a9",
"mode": "hierarchical",
"rules": {
"pre_processing_rules": [
{
"id": "remove_extra_spaces",
"enabled": true
},
{
"id": "remove_urls_emails",
"enabled": false
}
],
"segmentation": {
"separator": "**********page_ending**********",
"max_tokens": 1024,
"chunk_overlap": 0
},
"parent_mode": "paragraph",
"subchunk_segmentation": {
"separator": "\n",
"max_tokens": 512,
"chunk_overlap": 0
}
}
},
"name": "xxxx",
"created_from": "web",
"created_by": "17f71940-a7b5-4c77-b60f-2bd645c1ffa0",
"created_at": 1750464191,
"tokens": null,
"indexing_status": "waiting",
"completed_at": null,
"updated_at": 1750464191,
"indexing_latency": null,
"error": null,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"archived": false,
"segment_count": 0,
"average_segment_length": 0,
"hit_count": null,
"display_status": "queuing",
"doc_form": "hierarchical_model",
"doc_language": "Chinese Simplified"
}
```
</CodeGroup>
</Col>
</Row>
___
<hr className='ml-0 mr-0' />
<Heading
url='/datasets/{dataset_id}/documents/status/{action}'
method='PATCH'