Feat/dataset support api service (#1240)
Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: crazywoola <427733928@qq.com>
This commit is contained in:
zxhlyh
791
web/app/(commonLayout)/datasets/template/template.en.mdx
Normal file
791
web/app/(commonLayout)/datasets/template/template.en.mdx
Normal file
@@ -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
|
||||
Reference in New Issue
Block a user