OpenSource
/
dify
关注 4
点赞 0
派生 0
代码 工单 0 合并请求 0 版本发布 152 百科 动态
浏览代码

Feat/dataset support api service (#1240) 

Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
tags/0.3.24
zxhlyh 2 年前
父节点
46154c6705
当前提交
9dbb8acd4b
没有帐户链接到提交者的电子邮件
共有 14 个文件被更改，包括 1832 次插入 和 20 次删除
分列视图 显示文件统计
  1. 41
    0
      web/app/(commonLayout)/datasets/ApiServer.tsx
  2. 60
    0
      web/app/(commonLayout)/datasets/Container.tsx
  3. 12
    7
      web/app/(commonLayout)/datasets/Datasets.tsx
  4. 28
    0
      web/app/(commonLayout)/datasets/Doc.tsx
  5. 2
    6
      web/app/(commonLayout)/datasets/page.tsx
  6. 791
    0
      web/app/(commonLayout)/datasets/template/template.en.mdx
  7. 792
    0
      web/app/(commonLayout)/datasets/template/template.zh.mdx
  8. 55
    0
      web/app/components/base/tab-slider/index.tsx
  9. 1
    1
      web/app/components/develop/secret-key/secret-key-button.tsx
  10. 25
    5
      web/app/components/develop/secret-key/secret-key-modal.tsx
  11. 1
    1
      web/i18n/lang/app-api.zh.ts
  12. 2
    0
      web/i18n/lang/dataset.en.ts
  13. 2
    0
      web/i18n/lang/dataset.zh.ts
  14. 20
    0
      web/service/datasets.ts

+ 41
- 0
web/app/(commonLayout)/datasets/ApiServer.tsx 查看文件

@@ -0,0 +1,41 @@
'use client'

import type { FC } from 'react'
import { useTranslation } from 'react-i18next'
import CopyFeedback from '@/app/components/base/copy-feedback'
import SecretKeyButton from '@/app/components/develop/secret-key/secret-key-button'
import { randomString } from '@/utils'

type ApiServerProps = {
apiBaseUrl: string
}
const ApiServer: FC<ApiServerProps> = ({
apiBaseUrl,
}) => {
const { t } = useTranslation()

return (
<div className='flex items-center'>
<div className='flex items-center mr-2 pl-1.5 pr-1 h-8 bg-white/80 border-[0.5px] border-white rounded-lg'>
<div className='mr-0.5 px-1.5 h-5 border border-gray-200 text-[11px] text-gray-500 rounded-md'>{t('appApi.apiServer')}</div>
<div className='px-1 w-[248px] text-[13px] font-medium text-gray-800'>{apiBaseUrl}</div>
<div className='mx-1 w-[1px] h-[14px] bg-gray-200'></div>
<CopyFeedback
content={apiBaseUrl}
selectorId={randomString(8)}
className={'!w-6 !h-6 hover:bg-gray-200'}
/>
</div>
<div className='flex items-center mr-2 px-3 h-8 bg-[#ECFDF3] text-xs font-semibold text-[#039855] rounded-lg border-[0.5px] border-[#D1FADF]'>
{t('appApi.ok')}
</div>
<SecretKeyButton
className='flex-shrink-0 !h-8 bg-white'
textCls='!text-gray-700 font-medium'
iconCls='stroke-[1.2px]'
/>
</div>
)
}

export default ApiServer

+ 60
- 0
web/app/(commonLayout)/datasets/Container.tsx 查看文件

@@ -0,0 +1,60 @@
'use client'

import { useRef, useState } from 'react'
import { useTranslation } from 'react-i18next'
import useSWR from 'swr'
import Datasets from './Datasets'
import DatasetFooter from './DatasetFooter'
import ApiServer from './ApiServer'
import Doc from './Doc'
import TabSlider from '@/app/components/base/tab-slider'
import { fetchDatasetApiBaseUrl } from '@/service/datasets'

const Container = () => {
const { t } = useTranslation()
const options = [
{
value: 'dataset',
text: t('dataset.datasets'),
},
{
value: 'api',
text: t('dataset.datasetsApi'),
},
]
const [activeTab, setActiveTab] = useState('dataset')
const containerRef = useRef<HTMLDivElement>(null)
const { data } = useSWR(activeTab === 'dataset' ? null : '/datasets/api-base-info', fetchDatasetApiBaseUrl)

return (
<div ref={containerRef} className='grow relative flex flex-col bg-gray-100 overflow-y-auto'>
<div className='sticky top-0 flex justify-between pt-4 px-12 pb-2 h-14 bg-gray-100 z-10'>
<TabSlider
value={activeTab}
onChange={newActiveTab => setActiveTab(newActiveTab)}
options={options}
/>
{
activeTab === 'api' && (
<ApiServer apiBaseUrl={data?.api_base_url || ''} />
)
}
</div>
{
activeTab === 'dataset' && (
<div className=''>
<Datasets containerRef={containerRef}/>
<DatasetFooter />
</div>
)
}
{
activeTab === 'api' && (
<Doc apiBaseUrl={data?.api_base_url || ''} />
)
}
</div>
)
}

export default Container

+ 12
- 7
web/app/(commonLayout)/datasets/Datasets.tsx 查看文件

@@ -7,7 +7,7 @@ import NewDatasetCard from './NewDatasetCard'
import DatasetCard from './DatasetCard'
import type { DataSetListResponse } from '@/models/datasets'
import { fetchDatasets } from '@/service/datasets'
import { useAppContext, useSelector } from '@/context/app-context'
import { useAppContext } from '@/context/app-context'

const getKey = (pageIndex: number, previousPageData: DataSetListResponse) => {
if (!pageIndex || previousPageData.has_more)
@@ -15,11 +15,16 @@ const getKey = (pageIndex: number, previousPageData: DataSetListResponse) => {
return null
}

const Datasets = () => {
type Props = {
containerRef: React.RefObject<HTMLDivElement>
}

const Datasets = ({
containerRef,
}: Props) => {
const { isCurrentWorkspaceManager } = useAppContext()
const { data, isLoading, setSize, mutate } = useSWRInfinite(getKey, fetchDatasets, { revalidateFirstPage: false, revalidateAll: true })
const loadingStateRef = useRef(false)
const pageContainerRef = useSelector(state => state.pageContainerRef)
const anchorRef = useRef<HTMLAnchorElement>(null)

useEffect(() => {
@@ -29,19 +34,19 @@ const Datasets = () => {
useEffect(() => {
const onScroll = debounce(() => {
if (!loadingStateRef.current) {
const { scrollTop, clientHeight } = pageContainerRef.current!
const { scrollTop, clientHeight } = containerRef.current!
const anchorOffset = anchorRef.current!.offsetTop
if (anchorOffset - scrollTop - clientHeight < 100)
setSize(size => size + 1)
}
}, 50)

pageContainerRef.current?.addEventListener('scroll', onScroll)
return () => pageContainerRef.current?.removeEventListener('scroll', onScroll)
containerRef.current?.addEventListener('scroll', onScroll)
return () => containerRef.current?.removeEventListener('scroll', onScroll)
}, [])

return (
<nav className='grid content-start grid-cols-1 gap-4 px-12 pt-8 sm:grid-cols-2 md:grid-cols-3 lg:grid-cols-4 grow shrink-0'>
<nav className='grid content-start grid-cols-1 gap-4 px-12 pt-2 sm:grid-cols-2 md:grid-cols-3 lg:grid-cols-4 grow shrink-0'>
{ isCurrentWorkspaceManager && <NewDatasetCard ref={anchorRef} /> }
{data?.map(({ data: datasets }) => datasets.map(dataset => (
<DatasetCard key={dataset.id} dataset={dataset} onDelete={mutate} />),

+ 28
- 0
web/app/(commonLayout)/datasets/Doc.tsx 查看文件

@@ -0,0 +1,28 @@
'use client'

import type { FC } from 'react'
import { useContext } from 'use-context-selector'
import TemplateEn from './template/template.en.mdx'
import TemplateZh from './template/template.zh.mdx'
import I18n from '@/context/i18n'

type DocProps = {
apiBaseUrl: string
}
const Doc: FC<DocProps> = ({
apiBaseUrl,
}) => {
const { locale } = useContext(I18n)

return (
<article className='mx-12 pt-16 bg-white rounded-t-xl prose prose-xl'>
{
locale === 'en'
? <TemplateEn apiBaseUrl={apiBaseUrl} />
: <TemplateZh apiBaseUrl={apiBaseUrl} />
}
</article>
)
}

export default Doc

+ 2
- 6
web/app/(commonLayout)/datasets/page.tsx 查看文件

@@ -1,12 +1,8 @@
import Datasets from './Datasets'
import DatasetFooter from './DatasetFooter'
import Container from './Container'

const AppList = async () => {
return (
<div className='flex flex-col overflow-auto bg-gray-100 shrink-0 grow'>
<Datasets />
<DatasetFooter />
</div >
<Container />
)
}


+ 791
- 0
web/app/(commonLayout)/datasets/template/template.en.mdx 查看文件

@@ -0,0 +1,791 @@
import { CodeGroup } from '@/app/components/develop/code.tsx'
import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from '@/app/components/develop/md.tsx'

# Dataset API
<br/>
<br/>
<Heading
url='/datasets'
method='POST'
title='Create an empty dataset'
name='#create_empty_dataset'
/>
<Row>
<Col>
### Request Body
<Properties>
<Property name='name' type='string' key='name'>
Dataset name
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup
title="Request"
tag="POST"
label="/datasets"
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name"}'`}
>
```bash {{ title: 'cURL' }}
curl --location --request POST '${apiBaseUrl}/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='Dataset list'
name='#dataset_list'
/>
<Row>
<Col>
### Path Query
<Properties>
<Property name='page' type='string' key='page'>
Page number
</Property>
<Property name='limit' type='string' key='limit'>
Number of items returned, default 20, range 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": "name",
"description": "desc",
"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='Create a document from text'
name='#create_by_text'
/>
<Row>
<Col>
This api is based on an existing dataset and creates a new document through text based on this dataset.

### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
</Properties>

### Request Body
<Properties>
<Property name='name' type='string' key='name'>
Document name
</Property>
<Property name='text' type='string' key='text'>
Document content
</Property>
<Property name='indexing_technique' type='string' key='indexing_technique'>
Index mode
- high_quality High quality: embedding using embedding model, built as vector database index
- economy Economy: Build using inverted index of Keyword Table Index
</Property>
<Property name='process_rule' type='object' key='process_rule'>
Processing rules
- mode (string) Cleaning, segmentation mode, automatic / custom
- rules (text) Custom rules (in automatic mode, this field is empty)
- pre_processing_rules (array[object]) Preprocessing rules
- id (string) Unique identifier for the preprocessing rule
- enumerate
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
- remove_urls_emails Delete URL, email address
- enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
- segmentation (object) segmentation rules
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
- max_tokens Maximum length (token) defaults to 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='Create documents from files'
name='#create_by_file'
/>
<Row>
<Col>
This api is based on an existing dataset and creates a new document through a file based on this dataset.
### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
</Properties>

### Request Body
<Properties>
<Property name='original_document_id' type='string' key='original_document_id'>
Source document ID (optional)
- Used to re-upload the document or modify the document cleaning and segmentation configuration. The missing information is copied from the source document
- The source document cannot be an archived document
- When original_document_id is passed in, the update operation is performed on behalf of the document. process_rule is a fillable item. If not filled in, the segmentation method of the source document will be used by defaul
- When original_document_id is not passed in, the new operation is performed on behalf of the document, and process_rule is required
</Property>
<Property name='file' type='multipart/form-data' key='file'>
Files that need to be uploaded.
</Property>
<Property name='indexing_technique' type='string' key='indexing_technique'>
Index mode
- high_quality High quality: embedding using embedding model, built as vector database index
- economy Economy: Build using inverted index of Keyword Table Index
</Property>
<Property name='process_rule' type='object' key='process_rule'>
Processing rules
- mode (string) Cleaning, segmentation mode, automatic / custom
- rules (text) Custom rules (in automatic mode, this field is empty)
- pre_processing_rules (array[object]) Preprocessing rules
- id (string) Unique identifier for the preprocessing rule
- enumerate
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
- remove_urls_emails Delete URL, email address
- enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
- segmentation (object) segmentation rules
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
- max_tokens Maximum length (token) defaults to 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='Update document via text'
name='#update_by_text'
/>
<Row>
<Col>
This api is based on an existing dataset and updates the document through text based on this dataset.

### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
<Property name='document_id' type='string' key='document_id'>
Document ID
</Property>
</Properties>

### Request Body
<Properties>
<Property name='name' type='string' key='name'>
Document name (optional)
</Property>
<Property name='text' type='string' key='text'>
Document content (optional)
</Property>
<Property name='process_rule' type='object' key='process_rule'>
Processing rules
- mode (string) Cleaning, segmentation mode, automatic / custom
- rules (text) Custom rules (in automatic mode, this field is empty)
- pre_processing_rules (array[object]) Preprocessing rules
- id (string) Unique identifier for the preprocessing rule
- enumerate
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
- remove_urls_emails Delete URL, email address
- enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
- segmentation (object) segmentation rules
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
- max_tokens Maximum length (token) defaults to 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='Update a document from a file'
name='#update_by_file'
/>
<Row>
<Col>
This api is based on an existing dataset, and updates documents through files based on this dataset

### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
<Property name='document_id' type='string' key='document_id'>
Document ID
</Property>
</Properties>

### Request Body
<Properties>
<Property name='name' type='string' key='name'>
Document name (optional)
</Property>
<Property name='file' type='multipart/form-data' key='file'>
Files to be uploaded
</Property>
<Property name='process_rule' type='object' key='process_rule'>
Processing rules
- mode (string) Cleaning, segmentation mode, automatic / custom
- rules (text) Custom rules (in automatic mode, this field is empty)
- pre_processing_rules (array[object]) Preprocessing rules
- id (string) Unique identifier for the preprocessing rule
- enumerate
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
- remove_urls_emails Delete URL, email address
- enabled (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
- segmentation (object) segmentation rules
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
- max_tokens Maximum length (token) defaults to 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='Get document embedding status (progress)'
name='#indexing_status'
/>
<Row>
<Col>
### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
<Property name='batch' type='string' key='batch'>
Batch number of uploaded documents
</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='Delete document'
name='#delete_document'
/>
<Row>
<Col>
### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
<Property name='document_id' type='string' key='document_id'>
Document 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='Dataset document list'
name='#dataset_document_list'
/>
<Row>
<Col>
### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
</Properties>

### Path Query
<Properties>
<Property name='keyword' type='string' key='keyword'>
Search keywords, currently only search document names(optional)
</Property>
<Property name='page' type='string' key='page'>
Page number(optional)
</Property>
<Property name='limit' type='string' key='limit'>
Number of items returned, default 20, range 1-100(optional)
</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='Add segment'
name='#create_new_segment'
/>
<Row>
<Col>
### Path Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Dataset ID
</Property>
<Property name='document_id' type='string' key='document_id'>
Document ID
</Property>
</Properties>

### Request Body
<Properties>
<Property name='segments' type='object list' key='segments'>
segments (object list) Segmented content
- content (text) Text content/question content, required
- answer(text) Answer content, if the mode of the data set is qa mode, pass the value(optional)
- keywords(list) Keywords(optional)
</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>

---

Error message
- **document_indexing**: Document indexing failed
- **provider_not_initialize**: Embedding model is not configured
- **not_found**, Document does not exist
- **dataset_name_duplicate**: Duplicate dataset name
- **provider_quota_exceeded**: Model quota exceeds limit
- **dataset_not_initialized**: The dataset has not been initialized yet
- **unsupported_file_type**: Unsupported file types.
- Currently only supports, txt, markdown, md, pdf, html, htm, xlsx, docx, csv
- **too_many_files**: There are too many files. Currently, only a single file is uploaded
- **file_too_large*: The file is too large, support below 15M based on you environment configuration

+ 792
- 0
web/app/(commonLayout)/datasets/template/template.zh.mdx 查看文件

@@ -0,0 +1,792 @@
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

+ 55
- 0
web/app/components/base/tab-slider/index.tsx 查看文件

@@ -0,0 +1,55 @@
import type { FC } from 'react'

type Option = {
value: string
text: string
}
type TabSliderProps = {
value: string
onChange: (v: string) => void
options: Option[]
}
const TabSlider: FC<TabSliderProps> = ({
value,
onChange,
options,
}) => {
const currentIndex = options.findIndex(option => option.value === value)
const current = options[currentIndex]

return (
<div className='relative flex p-0.5 rounded-lg bg-gray-200'>
{
options.map((option, index) => (
<div
key={option.value}
className={`
flex justify-center items-center w-[118px] h-7 text-[13px]
font-semibold text-gray-600 rounded-[7px] cursor-pointer
hover:bg-gray-50
${index !== options.length - 1 && 'mr-[1px]'}
`}
onClick={() => onChange(option.value)}
>
{option.text}
</div>
))
}
{
current && (
<div
className={`
absolute flex justify-center items-center w-[118px] h-7 bg-white text-[13px] font-semibold text-primary-600
border-[0.5px] border-gray-200 rounded-[7px] shadow-xs transition-transform
`}
style={{ transform: `translateX(${currentIndex * 118 + 1}px)` }}
>
{current.text}
</div>
)
}
</div>
)
}

export default TabSlider

+ 1
- 1
web/app/components/develop/secret-key/secret-key-button.tsx 查看文件

@@ -7,7 +7,7 @@ import SecretKeyModal from '@/app/components/develop/secret-key/secret-key-modal

type ISecretKeyButtonProps = {
className?: string
appId: string
appId?: string
iconCls?: string
textCls?: string
}

+ 25
- 5
web/app/components/develop/secret-key/secret-key-modal.tsx 查看文件

@@ -12,7 +12,16 @@ import SecretKeyGenerateModal from './secret-key-generate'
import s from './style.module.css'
import Modal from '@/app/components/base/modal'
import Button from '@/app/components/base/button'
import { createApikey, delApikey, fetchApiKeysList } from '@/service/apps'
import {
createApikey as createAppApikey,
delApikey as delAppApikey,
fetchApiKeysList as fetchAppApiKeysList,
} from '@/service/apps'
import {
createApikey as createDatasetApikey,
delApikey as delDatasetApikey,
fetchApiKeysList as fetchDatasetApiKeysList,
} from '@/service/datasets'
import type { CreateApiKeyResponse } from '@/models/app'
import Tooltip from '@/app/components/base/tooltip'
import Loading from '@/app/components/base/loading'
@@ -22,7 +31,7 @@ import { useAppContext } from '@/context/app-context'

type ISecretKeyModalProps = {
isShow: boolean
appId: string
appId?: string
onClose: () => void
}

@@ -37,7 +46,10 @@ const SecretKeyModal = ({
const [isVisible, setVisible] = useState(false)
const [newKey, setNewKey] = useState<CreateApiKeyResponse | undefined>(undefined)
const { mutate } = useSWRConfig()
const commonParams = { url: `/apps/${appId}/api-keys`, params: {} }
const commonParams = appId
? { url: `/apps/${appId}/api-keys`, params: {} }
: { url: '/datasets/api-keys', params: {} }
const fetchApiKeysList = appId ? fetchAppApiKeysList : fetchDatasetApiKeysList
const { data: apiKeysList } = useSWR(commonParams, fetchApiKeysList)

const [delKeyID, setDelKeyId] = useState('')
@@ -64,12 +76,20 @@ const SecretKeyModal = ({
if (!delKeyID)
return

await delApikey({ url: `/apps/${appId}/api-keys/${delKeyID}`, params: {} })
const delApikey = appId ? delAppApikey : delDatasetApikey
const params = appId
? { url: `/apps/${appId}/api-keys/${delKeyID}`, params: {} }
: { url: `/datasets/api-keys/${delKeyID}`, params: {} }
await delApikey(params)
mutate(commonParams)
}

const onCreate = async () => {
const res = await createApikey({ url: `/apps/${appId}/api-keys`, body: {} })
const params = appId
? { url: `/apps/${appId}/api-keys`, body: {} }
: { url: '/datasets/api-keys', body: {} }
const createApikey = appId ? createAppApikey : createDatasetApikey
const res = await createApikey(params)
setVisible(true)
setNewKey(res)
mutate(commonParams)

+ 1
- 1
web/i18n/lang/app-api.zh.ts 查看文件

@@ -12,7 +12,7 @@ const translation = {
never: '从未',
apiKeyModal: {
apiSecretKey: 'API 密钥',
apiSecretKeyTips: '如果不想你的应用 API 被滥用，请保护好你的 API Key :) 最佳实践是避免在前端代码中明文引用。',
apiSecretKeyTips: '如果不想你的 API 被滥用，请保护好你的 API Key :) 最佳实践是避免在前端代码中明文引用。',
createNewSecretKey: '创建密钥',
secretKey: '密钥',
created: '创建时间',

+ 2
- 0
web/i18n/lang/dataset.en.ts 查看文件

@@ -18,6 +18,8 @@ const translation = {
intro6: ' as a standalone ChatGPT index plug-in to publish',
unavailable: 'Unavailable',
unavailableTip: 'Embedding model is not available, the default embedding model needs to be configured',
datasets: 'DATASETS',
datasetsApi: 'API',
}

export default translation

+ 2
- 0
web/i18n/lang/dataset.zh.ts 查看文件

@@ -18,6 +18,8 @@ const translation = {
intro6: '为独立的 ChatGPT 插件发布使用',
unavailable: '不可用',
unavailableTip: '由于 embedding 模型不可用，需要配置默认 embedding 模型',
datasets: '数据集',
datasetsApi: 'API',
}

export default translation

+ 20
- 0
web/service/datasets.ts 查看文件

@@ -22,6 +22,10 @@ import type {
createDocumentResponse,
} from '@/models/datasets'
import type { CommonResponse, DataSourceNotionWorkspace } from '@/models/common'
import type {
ApikeysListResponse,
CreateApiKeyResponse,
} from '@/models/app'

// apis for documents in a dataset

@@ -192,3 +196,19 @@ export const fetchFileIndexingEstimate: Fetcher<FileIndexingEstimateResponse, an
export const fetchNotionPagePreview: Fetcher<{ content: string }, { workspaceID: string; pageID: string; pageType: string }> = ({ workspaceID, pageID, pageType }) => {
return get<{ content: string }>(`notion/workspaces/${workspaceID}/pages/${pageID}/${pageType}/preview`)
}

export const fetchApiKeysList: Fetcher<ApikeysListResponse, { url: string; params: Record<string, any> }> = ({ url, params }) => {
return get<ApikeysListResponse>(url, params)
}

export const delApikey: Fetcher<CommonResponse, { url: string; params: Record<string, any> }> = ({ url, params }) => {
return del<CommonResponse>(url, params)
}

export const createApikey: Fetcher<CreateApiKeyResponse, { url: string; body: Record<string, any> }> = ({ url, body }) => {
return post<CreateApiKeyResponse>(url, body)
}

export const fetchDatasetApiBaseUrl: Fetcher<{ api_base_url: string }, string> = (url) => {
return get<{ api_base_url: string }>(url)
}

撰写 预览
正在加载...
取消
保存