793 lines
25 KiB
Plaintext
793 lines
25 KiB
Plaintext
![]() |
import { CodeGroup } from '@/app/components/develop/code.tsx'
|
|||
|
import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from '@/app/components/develop/md.tsx'
|
|||
|
|
|||
|
# 数据集 API
|
|||
|
<br/>
|
|||
|
<br/>
|
|||
|
<Heading
|
|||
|
url='/datasets'
|
|||
|
method='POST'
|
|||
|
title='创建空数据集'
|
|||
|
name='#create_empty_dataset'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='name' type='string' key='name'>
|
|||
|
数据集名称
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets"
|
|||
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name"}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request POST 'https://api.dify.ai/v1/datasets' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--header 'Content-Type: application/json' \
|
|||
|
--data-raw '{
|
|||
|
"name": "name"
|
|||
|
}'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"id": "",
|
|||
|
"name": "name",
|
|||
|
"description": null,
|
|||
|
"provider": "vendor",
|
|||
|
"permission": "only_me",
|
|||
|
"data_source_type": null,
|
|||
|
"indexing_technique": null,
|
|||
|
"app_count": 0,
|
|||
|
"document_count": 0,
|
|||
|
"word_count": 0,
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695636173,
|
|||
|
"updated_by": "",
|
|||
|
"updated_at": 1695636173,
|
|||
|
"embedding_model": null,
|
|||
|
"embedding_model_provider": null,
|
|||
|
"embedding_available": null
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets'
|
|||
|
method='GET'
|
|||
|
title='数据集列表'
|
|||
|
name='#dataset_list'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Path Query
|
|||
|
<Properties>
|
|||
|
<Property name='page' type='string' key='page'>
|
|||
|
页码
|
|||
|
</Property>
|
|||
|
<Property name='limit' type='string' key='limit'>
|
|||
|
返回条数,默认 20,范围 1-100
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets"
|
|||
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request GET 'https://api.dify.ai/v1/datasets?page=1&limit=20' \
|
|||
|
--header 'Authorization: Bearer {api_key}'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"data": [
|
|||
|
{
|
|||
|
"id": "",
|
|||
|
"name": "数据集名称",
|
|||
|
"description": "描述信息",
|
|||
|
"permission": "only_me",
|
|||
|
"data_source_type": "upload_file",
|
|||
|
"indexing_technique": "",
|
|||
|
"app_count": 2,
|
|||
|
"document_count": 10,
|
|||
|
"word_count": 1200,
|
|||
|
"created_by": "",
|
|||
|
"created_at": "",
|
|||
|
"updated_by": "",
|
|||
|
"updated_at": ""
|
|||
|
},
|
|||
|
...
|
|||
|
],
|
|||
|
"has_more": true,
|
|||
|
"limit": 20,
|
|||
|
"total": 50,
|
|||
|
"page": 1
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/document/create_by_text'
|
|||
|
method='POST'
|
|||
|
title='通过文本创建文档'
|
|||
|
name='#create_by_text'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
此接口基于已存在数据集,在此数据集的基础上通过文本创建新的文档
|
|||
|
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='name' type='string' key='name'>
|
|||
|
文档名称
|
|||
|
</Property>
|
|||
|
<Property name='text' type='string' key='text'>
|
|||
|
文档内容
|
|||
|
</Property>
|
|||
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
|||
|
索引方式
|
|||
|
- high_quality 高质量:使用 embedding 模型进行嵌入,构建为向量数据库索引
|
|||
|
- economy 经济:使用 Keyword Table Index 的倒排索引进行构建
|
|||
|
</Property>
|
|||
|
<Property name='process_rule' type='object' key='process_rule'>
|
|||
|
处理规则
|
|||
|
- mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义
|
|||
|
- rules (text) 自定义规则(自动模式下,该字段为空)
|
|||
|
- pre_processing_rules (array[object]) 预处理规则
|
|||
|
- id (string) 预处理规则的唯一标识符
|
|||
|
- 枚举:
|
|||
|
- remove_extra_spaces 替换连续空格、换行符、制表符
|
|||
|
- remove_urls_emails 删除 URL、电子邮件地址
|
|||
|
- enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
|
|||
|
- segmentation (object) 分段规则
|
|||
|
- separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
|
|||
|
- max_tokens 最大长度 (token) 默认为 1000
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets/{dataset_id}/document/create_by_text"
|
|||
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "text","text": "text","indexing_technique": "high_quality","process_rule": {"mode": "automatic"}}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_text' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--header 'Content-Type: application/json' \
|
|||
|
--data-raw '{
|
|||
|
"name": "text",
|
|||
|
"text": "text",
|
|||
|
"indexing_technique": "high_quality",
|
|||
|
"process_rule": {
|
|||
|
"mode": "automatic"
|
|||
|
}
|
|||
|
}'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"document": {
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"data_source_type": "upload_file",
|
|||
|
"data_source_info": {
|
|||
|
"upload_file_id": ""
|
|||
|
},
|
|||
|
"dataset_process_rule_id": "",
|
|||
|
"name": "text.txt",
|
|||
|
"created_from": "api",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695690280,
|
|||
|
"tokens": 0,
|
|||
|
"indexing_status": "waiting",
|
|||
|
"error": null,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"archived": false,
|
|||
|
"display_status": "queuing",
|
|||
|
"word_count": 0,
|
|||
|
"hit_count": 0,
|
|||
|
"doc_form": "text_model"
|
|||
|
},
|
|||
|
"batch": ""
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/document/create_by_file'
|
|||
|
method='POST'
|
|||
|
title='通过文件创建文档 '
|
|||
|
name='#create_by_file'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
此接口基于已存在数据集,在此数据集的基础上通过文件创建新的文档
|
|||
|
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='original_document_id' type='string' key='original_document_id'>
|
|||
|
源文档 ID (选填)
|
|||
|
- 用于重新上传文档或修改文档清洗、分段配置,缺失的信息从源文档复制
|
|||
|
- 源文档不可为归档的文档
|
|||
|
- 当传入 original_document_id 时,代表文档进行更新操作,process_rule 为可填项目,不填默认使用源文档的分段方式
|
|||
|
- 未传入 original_document_id 时,代表文档进行新增操作,process_rule 为必填
|
|||
|
</Property>
|
|||
|
<Property name='file' type='multipart/form-data' key='file'>
|
|||
|
需要上传的文件。
|
|||
|
</Property>
|
|||
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
|||
|
索引方式
|
|||
|
- high_quality 高质量:使用 embedding 模型进行嵌入,构建为向量数据库索引
|
|||
|
- economy 经济:使用 Keyword Table Index 的倒排索引进行构建
|
|||
|
</Property>
|
|||
|
<Property name='process_rule' type='object' key='process_rule'>
|
|||
|
处理规则
|
|||
|
- mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义。
|
|||
|
- rules (text) 自定义规则(自动模式下,该字段为空)
|
|||
|
- pre_processing_rules (array[object]) 预处理规则
|
|||
|
- id (string) 预处理规则的唯一标识符
|
|||
|
- 枚举:
|
|||
|
- remove_extra_spaces 替换连续空格、换行符、制表符
|
|||
|
- remove_urls_emails 删除 URL、电子邮件地址
|
|||
|
- enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值。
|
|||
|
- segmentation (object) 分段规则
|
|||
|
- separator 自定义分段标识符,目前仅允许设置一个分隔符,默认为 \n
|
|||
|
- max_tokens 最大长度 (token) 默认为 1000
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets/{dataset_id}/document/create_by_file"
|
|||
|
targetCode={`curl --location POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_file' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--form 'data="{\"name\":\"Dify\",\"indexing_technique\":\"high_quality\",\"process_rule\":{\"rules\":{\"pre_processing_rules\":[{\"id\":\"remove_extra_spaces\",\"enabled\":true},{\"id\":\"remove_urls_emails\",\"enabled\":true}],\"segmentation\":{\"separator\":\"###\",\"max_tokens\":500}},\"mode\":\"custom\"}}";type=text/plain' \
|
|||
|
--form 'file=@"/path/to/file"'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"document": {
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"data_source_type": "upload_file",
|
|||
|
"data_source_info": {
|
|||
|
"upload_file_id": ""
|
|||
|
},
|
|||
|
"dataset_process_rule_id": "",
|
|||
|
"name": "Dify.txt",
|
|||
|
"created_from": "api",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695308667,
|
|||
|
"tokens": 0,
|
|||
|
"indexing_status": "waiting",
|
|||
|
"error": null,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"archived": false,
|
|||
|
"display_status": "queuing",
|
|||
|
"word_count": 0,
|
|||
|
"hit_count": 0,
|
|||
|
"doc_form": "text_model"
|
|||
|
},
|
|||
|
"batch": ""
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/documents/{document_id}/update_by_text'
|
|||
|
method='POST'
|
|||
|
title='通过文本更新文档 '
|
|||
|
name='#update_by_text'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
此接口基于已存在数据集,在此数据集的基础上通过文本更新文档
|
|||
|
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
<Property name='document_id' type='string' key='document_id'>
|
|||
|
文档 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='name' type='string' key='name'>
|
|||
|
文档名称 (选填)
|
|||
|
</Property>
|
|||
|
<Property name='text' type='string' key='text'>
|
|||
|
文档内容(选填)
|
|||
|
</Property>
|
|||
|
<Property name='process_rule' type='object' key='process_rule'>
|
|||
|
处理规则(选填)
|
|||
|
- mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义。
|
|||
|
- rules (text) 自定义规则(自动模式下,该字段为空)
|
|||
|
- pre_processing_rules (array[object]) 预处理规则
|
|||
|
- id (string) 预处理规则的唯一标识符
|
|||
|
- 枚举:
|
|||
|
- remove_extra_spaces 替换连续空格、换行符、制表符
|
|||
|
- remove_urls_emails 删除 URL、电子邮件地址
|
|||
|
- enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值。
|
|||
|
- segmentation (object) 分段规则
|
|||
|
- separator 自定义分段标识符,目前仅允许设置一个分隔符。默认为 \n
|
|||
|
- max_tokens 最大长度 (token) 默认为 1000
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets/{dataset_id}/documents/{document_id}/update_by_text"
|
|||
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name","text": "text"}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/update_by_text' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--header 'Content-Type: application/json' \
|
|||
|
--data-raw '{
|
|||
|
"name": "name",
|
|||
|
"text": "text"
|
|||
|
}'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"document": {
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"data_source_type": "upload_file",
|
|||
|
"data_source_info": {
|
|||
|
"upload_file_id": ""
|
|||
|
},
|
|||
|
"dataset_process_rule_id": "",
|
|||
|
"name": "name.txt",
|
|||
|
"created_from": "api",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695308667,
|
|||
|
"tokens": 0,
|
|||
|
"indexing_status": "waiting",
|
|||
|
"error": null,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"archived": false,
|
|||
|
"display_status": "queuing",
|
|||
|
"word_count": 0,
|
|||
|
"hit_count": 0,
|
|||
|
"doc_form": "text_model"
|
|||
|
},
|
|||
|
"batch": ""
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/documents/{document_id}/update_by_file'
|
|||
|
method='POST'
|
|||
|
title='通过文件更新文档 '
|
|||
|
name='#update_by_file'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
此接口基于已存在数据集,在此数据集的基础上通过文件更新文档的操作。
|
|||
|
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
<Property name='document_id' type='string' key='document_id'>
|
|||
|
文档 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='name' type='string' key='name'>
|
|||
|
文档名称 (选填)
|
|||
|
</Property>
|
|||
|
<Property name='file' type='multipart/form-data' key='file'>
|
|||
|
需要上传的文件
|
|||
|
</Property>
|
|||
|
<Property name='process_rule' type='object' key='process_rule'>
|
|||
|
处理规则(选填)
|
|||
|
- mode (string) 清洗、分段模式 ,automatic 自动 / custom 自定义。
|
|||
|
- rules (text) 自定义规则(自动模式下,该字段为空)
|
|||
|
- pre_processing_rules (array[object]) 预处理规则
|
|||
|
- id (string) 预处理规则的唯一标识符
|
|||
|
- 枚举:
|
|||
|
- remove_extra_spaces 替换连续空格、换行符、制表符
|
|||
|
- remove_urls_emails 删除 URL、电子邮件地址
|
|||
|
- enabled (bool) 是否选中该规则,不传入文档 ID 时代表默认值
|
|||
|
- segmentation (object) 分段规则
|
|||
|
- separator 自定义分段标识符,目前仅允许设置一个分隔符,默认为 \n
|
|||
|
- max_tokens 最大长度 (token) 默认为 1000
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets/{dataset_id}/documents/{document_id}/update_by_file"
|
|||
|
targetCode={`curl --location POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/{document_id}/create_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location POST 'https://api.dify.ai/v1/datasets/{dataset_id}/document/{document_id}/create_by_file' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--form 'data="{\"name\":\"Dify\",\"indexing_technique\":\"high_quality\",\"process_rule\":{\"rules\":{\"pre_processing_rules\":[{\"id\":\"remove_extra_spaces\",\"enabled\":true},{\"id\":\"remove_urls_emails\",\"enabled\":true}],\"segmentation\":{\"separator\":\"###\",\"max_tokens\":500}},\"mode\":\"custom\"}}";type=text/plain' \
|
|||
|
--form 'file=@"/path/to/file"'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"document": {
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"data_source_type": "upload_file",
|
|||
|
"data_source_info": {
|
|||
|
"upload_file_id": ""
|
|||
|
},
|
|||
|
"dataset_process_rule_id": "",
|
|||
|
"name": "Dify.txt",
|
|||
|
"created_from": "api",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695308667,
|
|||
|
"tokens": 0,
|
|||
|
"indexing_status": "waiting",
|
|||
|
"error": null,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"archived": false,
|
|||
|
"display_status": "queuing",
|
|||
|
"word_count": 0,
|
|||
|
"hit_count": 0,
|
|||
|
"doc_form": "text_model"
|
|||
|
},
|
|||
|
"batch": "20230921150427533684"
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/batch/{batch}/indexing-status'
|
|||
|
method='GET'
|
|||
|
title='获取文档嵌入状态(进度)'
|
|||
|
name='#indexing_status'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
<Property name='batch' type='string' key='batch'>
|
|||
|
上传文档的批次号
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="GET"
|
|||
|
label="/datasets/{dataset_id}/batch/{batch}/indexing-status"
|
|||
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"data":[{
|
|||
|
"id": "",
|
|||
|
"indexing_status": "indexing",
|
|||
|
"processing_started_at": 1681623462.0,
|
|||
|
"parsing_completed_at": 1681623462.0,
|
|||
|
"cleaning_completed_at": 1681623462.0,
|
|||
|
"splitting_completed_at": 1681623462.0,
|
|||
|
"completed_at": null,
|
|||
|
"paused_at": null,
|
|||
|
"error": null,
|
|||
|
"stopped_at": null,
|
|||
|
"completed_segments": 24,
|
|||
|
"total_segments": 100
|
|||
|
}]
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/documents/{document_id}'
|
|||
|
method='DELETE'
|
|||
|
title='删除文档'
|
|||
|
name='#delete_document'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
<Property name='document_id' type='string' key='document_id'>
|
|||
|
文档 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="DELETE"
|
|||
|
label="/datasets/{dataset_id}/documents/{document_id}"
|
|||
|
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request DELETE 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"result": "success"
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/documents'
|
|||
|
method='GET'
|
|||
|
title='数据集文档列表'
|
|||
|
name='#dataset_document_list'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Path Query
|
|||
|
<Properties>
|
|||
|
<Property name='keyword' type='string' key='keyword'>
|
|||
|
搜索关键词,可选,目前仅搜索文档名称
|
|||
|
</Property>
|
|||
|
<Property name='page' type='string' key='page'>
|
|||
|
页码,可选
|
|||
|
</Property>
|
|||
|
<Property name='limit' type='string' key='limit'>
|
|||
|
返回条数,可选,默认 20,范围 1-100
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="GET"
|
|||
|
label="/datasets/{dataset_id}/documents"
|
|||
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request GET 'https://api.dify.ai/v1/datasets/{dataset_id}/documents' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"data": [
|
|||
|
{
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"data_source_type": "file_upload",
|
|||
|
"data_source_info": null,
|
|||
|
"dataset_process_rule_id": null,
|
|||
|
"name": "dify",
|
|||
|
"created_from": "",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1681623639,
|
|||
|
"tokens": 0,
|
|||
|
"indexing_status": "waiting",
|
|||
|
"error": null,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"archived": false
|
|||
|
},
|
|||
|
],
|
|||
|
"has_more": false,
|
|||
|
"limit": 20,
|
|||
|
"total": 9,
|
|||
|
"page": 1
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
<Heading
|
|||
|
url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
|||
|
method='POST'
|
|||
|
title='新增分段'
|
|||
|
name='#create_new_segment'
|
|||
|
/>
|
|||
|
<Row>
|
|||
|
<Col>
|
|||
|
### Path Params
|
|||
|
<Properties>
|
|||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|||
|
数据集 ID
|
|||
|
</Property>
|
|||
|
<Property name='document_id' type='string' key='document_id'>
|
|||
|
文档 ID
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
|
|||
|
### Request Body
|
|||
|
<Properties>
|
|||
|
<Property name='segments' type='object list' key='segments'>
|
|||
|
segments (object list) 分段内容
|
|||
|
- content (text) 文本内容/问题内容,必填
|
|||
|
- answer(text) 答案内容,非必填,如果数据集的模式为qa模式则传值
|
|||
|
- keywords(list) 关键字,非必填
|
|||
|
</Property>
|
|||
|
</Properties>
|
|||
|
</Col>
|
|||
|
<Col sticky>
|
|||
|
<CodeGroup
|
|||
|
title="Request"
|
|||
|
tag="POST"
|
|||
|
label="/datasets/{dataset_id}/documents/{document_id}/segments"
|
|||
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"segments": [{"content": "1","answer": "1","keywords": ["a"]}]}'`}
|
|||
|
>
|
|||
|
```bash {{ title: 'cURL' }}
|
|||
|
curl --location --request POST 'https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}/segments' \
|
|||
|
--header 'Authorization: Bearer {api_key}' \
|
|||
|
--header 'Content-Type: application/json' \
|
|||
|
--data-raw '{
|
|||
|
"segments": [
|
|||
|
{
|
|||
|
"content": "1",
|
|||
|
"answer": "1",
|
|||
|
"keywords": ["a"]
|
|||
|
}
|
|||
|
]
|
|||
|
}'
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
<CodeGroup title="Response">
|
|||
|
```json {{ title: 'Response' }}
|
|||
|
{
|
|||
|
"data": [{
|
|||
|
"id": "",
|
|||
|
"position": 1,
|
|||
|
"document_id": "",
|
|||
|
"content": "1",
|
|||
|
"answer": "1",
|
|||
|
"word_count": 25,
|
|||
|
"tokens": 0,
|
|||
|
"keywords": [
|
|||
|
"a"
|
|||
|
],
|
|||
|
"index_node_id": "",
|
|||
|
"index_node_hash": "",
|
|||
|
"hit_count": 0,
|
|||
|
"enabled": true,
|
|||
|
"disabled_at": null,
|
|||
|
"disabled_by": null,
|
|||
|
"status": "completed",
|
|||
|
"created_by": "",
|
|||
|
"created_at": 1695312007,
|
|||
|
"indexing_at": 1695312007,
|
|||
|
"completed_at": 1695312007,
|
|||
|
"error": null,
|
|||
|
"stopped_at": null
|
|||
|
}],
|
|||
|
"doc_form": "text_model"
|
|||
|
}
|
|||
|
```
|
|||
|
</CodeGroup>
|
|||
|
</Col>
|
|||
|
</Row>
|
|||
|
|
|||
|
---
|
|||
|
|
|||
|
错误信息
|
|||
|
- **document_indexing**: 文档索引失败
|
|||
|
- **provider_not_initialize**: Embedding 模型未配置
|
|||
|
- **not_found**,文档不存在
|
|||
|
- **dataset_name_duplicate**: 数据集名称重复
|
|||
|
- **provider_quota_exceeded**: 模型额度超过限制
|
|||
|
- **dataset_not_initialized**: 数据集还未初始化
|
|||
|
- **unsupported_file_type**: 不支持的文件类型
|
|||
|
- 目前只支持:txt, markdown, md, pdf, html, htm, xlsx, docx, csv
|
|||
|
- **too_many_files**: 文件数量过多,暂时只支持单一文件上传
|
|||
|
- **file_too_large*: 文件太大,默认支持15M以下, 具体需要参考环境变量配置
|