mirror of
https://github.com/langgenius/dify.git
synced 2024-11-16 11:42:29 +08:00
fix: doc (#1256)
This commit is contained in:
zxhlyh
GitHub
parent
5e511e01bf
commit
bcd744b6b7
|
|
@ -71,7 +71,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Query
|
### Query
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='page' type='string' key='page'>
|
<Property name='page' type='string' key='page'>
|
||||||
Page number
|
Page number
|
||||||
|
|
@ -136,7 +136,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<Col>
|
||||||
This api is based on an existing dataset and creates a new document through text based on this dataset.
|
This api is based on an existing dataset and creates a new document through text based on this dataset.
|
||||||
|
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -153,22 +153,22 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
||||||
Index mode
|
Index mode
|
||||||
- high_quality High quality: embedding using embedding model, built as vector database index
|
- <code>high_quality</code> High quality: embedding using embedding model, built as vector database index
|
||||||
- economy Economy: Build using inverted index of Keyword Table Index
|
- <code>economy</code> Economy: Build using inverted index of Keyword Table Index
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
Processing rules
|
Processing rules
|
||||||
- mode (string) Cleaning, segmentation mode, automatic / custom
|
- <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
||||||
- rules (text) Custom rules (in automatic mode, this field is empty)
|
- <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
||||||
- pre_processing_rules (array[object]) Preprocessing rules
|
- <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
||||||
- id (string) Unique identifier for the preprocessing rule
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
||||||
- enumerate
|
- enumerate
|
||||||
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
|
- <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
||||||
- remove_urls_emails Delete URL, email address
|
- <code>remove_urls_emails</code> 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.
|
- <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
||||||
- segmentation (object) segmentation rules
|
- <code>segmentation</code> (object) segmentation rules
|
||||||
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
- <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
||||||
- max_tokens Maximum length (token) defaults to 1000
|
- <code>max_tokens</code> Maximum length (token) defaults to 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -238,7 +238,8 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
This api is based on an existing dataset and creates a new document through a file based on this dataset.
|
This api is based on an existing dataset and creates a new document through a file based on this dataset.
|
||||||
### Path Params
|
|
||||||
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -259,22 +260,22 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
||||||
Index mode
|
Index mode
|
||||||
- high_quality High quality: embedding using embedding model, built as vector database index
|
- <code>high_quality</code> High quality: embedding using embedding model, built as vector database index
|
||||||
- economy Economy: Build using inverted index of Keyword Table Index
|
- <code>economy</code> Economy: Build using inverted index of Keyword Table Index
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
Processing rules
|
Processing rules
|
||||||
- mode (string) Cleaning, segmentation mode, automatic / custom
|
- <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
||||||
- rules (text) Custom rules (in automatic mode, this field is empty)
|
- <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
||||||
- pre_processing_rules (array[object]) Preprocessing rules
|
- <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
||||||
- id (string) Unique identifier for the preprocessing rule
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
||||||
- enumerate
|
- enumerate
|
||||||
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
|
- <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
||||||
- remove_urls_emails Delete URL, email address
|
- <code>remove_urls_emails</code> 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.
|
- <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
||||||
- segmentation (object) segmentation rules
|
- <code>segmentation</code> (object) segmentation rules
|
||||||
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
- <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
||||||
- max_tokens Maximum length (token) defaults to 1000
|
- <code>max_tokens</code> Maximum length (token) defaults to 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -338,7 +339,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<Col>
|
||||||
This api is based on an existing dataset and updates the document through text based on this dataset.
|
This api is based on an existing dataset and updates the document through text based on this dataset.
|
||||||
|
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -358,17 +359,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
Processing rules
|
Processing rules
|
||||||
- mode (string) Cleaning, segmentation mode, automatic / custom
|
- <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
||||||
- rules (text) Custom rules (in automatic mode, this field is empty)
|
- <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
||||||
- pre_processing_rules (array[object]) Preprocessing rules
|
- <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
||||||
- id (string) Unique identifier for the preprocessing rule
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
||||||
- enumerate
|
- enumerate
|
||||||
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
|
- <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
||||||
- remove_urls_emails Delete URL, email address
|
- <code>remove_urls_emails</code> 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.
|
- <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
||||||
- segmentation (object) segmentation rules
|
- <code>segmentation</code> (object) segmentation rules
|
||||||
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
- <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
||||||
- max_tokens Maximum length (token) defaults to 1000
|
- <code>max_tokens</code> Maximum length (token) defaults to 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -435,7 +436,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<Col>
|
||||||
This api is based on an existing dataset, and updates documents through files based on this dataset
|
This api is based on an existing dataset, and updates documents through files based on this dataset
|
||||||
|
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -455,17 +456,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
Processing rules
|
Processing rules
|
||||||
- mode (string) Cleaning, segmentation mode, automatic / custom
|
- <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
||||||
- rules (text) Custom rules (in automatic mode, this field is empty)
|
- <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
||||||
- pre_processing_rules (array[object]) Preprocessing rules
|
- <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
||||||
- id (string) Unique identifier for the preprocessing rule
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
||||||
- enumerate
|
- enumerate
|
||||||
- remove_extra_spaces Replace consecutive spaces, newlines, tabs
|
- <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
||||||
- remove_urls_emails Delete URL, email address
|
- <code>remove_urls_emails</code> 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.
|
- <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
||||||
- segmentation (object) segmentation rules
|
- <code>segmentation</code> (object) segmentation rules
|
||||||
- separator Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
- <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
||||||
- max_tokens Maximum length (token) defaults to 1000
|
- <code>max_tokens</code> Maximum length (token) defaults to 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -527,7 +528,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -582,7 +583,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -624,14 +625,14 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
|
|
||||||
### Path Query
|
### Query
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='keyword' type='string' key='keyword'>
|
<Property name='keyword' type='string' key='keyword'>
|
||||||
Search keywords, currently only search document names(optional)
|
Search keywords, currently only search document names(optional)
|
||||||
|
|
@ -699,7 +700,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Params
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
Dataset ID
|
Dataset ID
|
||||||
|
|
@ -712,10 +713,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
### Request Body
|
### Request Body
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='segments' type='object list' key='segments'>
|
<Property name='segments' type='object list' key='segments'>
|
||||||
segments (object list) Segmented content
|
- <code>content</code> (text) Text content/question content, required
|
||||||
- content (text) Text content/question content, required
|
- <code>answer</code> (text) Answer content, if the mode of the data set is qa mode, pass the value(optional)
|
||||||
- answer(text) Answer content, if the mode of the data set is qa mode, pass the value(optional)
|
- <code>keywords</code> (list) Keywords(optional)
|
||||||
- keywords(list) Keywords(optional)
|
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -778,14 +778,106 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### Error message
|
||||||
|
<Properties>
|
||||||
|
<Property name='code' type='string' key='code'>
|
||||||
|
Error code
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
<Properties>
|
||||||
|
<Property name='status' type='number' key='status'>
|
||||||
|
Error status
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
<Properties>
|
||||||
|
<Property name='message' type='string' key='message'>
|
||||||
Error message
|
Error message
|
||||||
- **document_indexing**: Document indexing failed
|
</Property>
|
||||||
- **provider_not_initialize**: Embedding model is not configured
|
</Properties>
|
||||||
- **not_found**, Document does not exist
|
</Col>
|
||||||
- **dataset_name_duplicate**: Duplicate dataset name
|
<Col>
|
||||||
- **provider_quota_exceeded**: Model quota exceeds limit
|
<CodeGroup title="Example">
|
||||||
- **dataset_not_initialized**: The dataset has not been initialized yet
|
```json {{ title: 'Response' }}
|
||||||
- **unsupported_file_type**: Unsupported file types.
|
{
|
||||||
- Currently only supports, txt, markdown, md, pdf, html, htm, xlsx, docx, csv
|
"code": "no_file_uploaded",
|
||||||
- **too_many_files**: There are too many files. Currently, only a single file is uploaded
|
"message": "Please upload your file.",
|
||||||
- **file_too_large*: The file is too large, support below 15M based on you environment configuration
|
"status": 400
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
<table className="max-w-auto border-collapse border border-slate-400" style={{ maxWidth: 'none', width: 'auto' }}>
|
||||||
|
<thead style={{ background: '#f9fafc' }}>
|
||||||
|
<tr>
|
||||||
|
<th class="p-2 border border-slate-300">code</th>
|
||||||
|
<th class="p-2 border border-slate-300">status</th>
|
||||||
|
<th class="p-2 border border-slate-300">message</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">no_file_uploaded</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Please upload your file.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">too_many_files</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Only one file is allowed.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">file_too_large</td>
|
||||||
|
<td class="p-2 border border-slate-300">413</td>
|
||||||
|
<td class="p-2 border border-slate-300">File size exceeded.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">unsupported_file_type</td>
|
||||||
|
<td class="p-2 border border-slate-300">415</td>
|
||||||
|
<td class="p-2 border border-slate-300">File type not allowed.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">high_quality_dataset_only</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Current operation only supports 'high-quality' datasets.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">dataset_not_initialized</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The dataset is still being initialized or indexing. Please wait a moment.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">archived_document_immutable</td>
|
||||||
|
<td class="p-2 border border-slate-300">403</td>
|
||||||
|
<td class="p-2 border border-slate-300">The archived document is not editable.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">dataset_name_duplicate</td>
|
||||||
|
<td class="p-2 border border-slate-300">409</td>
|
||||||
|
<td class="p-2 border border-slate-300">The dataset name already exists. Please modify your dataset name.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">invalid_action</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Invalid action.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">document_already_finished</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The document has been processed. Please refresh the page or go to the document details.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">document_indexing</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The document is being processed and cannot be edited.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">invalid_metadata</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The metadata content is incorrect. Please check and verify.</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
<div class="pb-4" />
|
||||||
|
|
|
||||||
|
|
@ -71,7 +71,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Query
|
### Query
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='page' type='string' key='page'>
|
<Property name='page' type='string' key='page'>
|
||||||
页码
|
页码
|
||||||
|
|
@ -136,7 +136,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<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
|
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
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -153,22 +153,22 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
||||||
索引方式
|
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
|
- <code>high_quality</code> 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
|
- <code>economy</code> 经济：使用 Keyword Table Index 的倒排索引进行构建
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
处理规则
|
处理规则
|
||||||
- mode (string) 清洗、分段模式 ，automatic 自动 / custom 自定义
|
- <code>mode</code> (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）
|
- <code>rules</code> (object) 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
|
- <code>pre_processing_rules</code> (array[object]) 预处理规则
|
||||||
- id (string) 预处理规则的唯一标识符
|
- <code>id</code> (string) 预处理规则的唯一标识符
|
||||||
- 枚举：
|
- 枚举：
|
||||||
- remove_extra_spaces 替换连续空格、换行符、制表符
|
- <code>remove_extra_spaces</code> 替换连续空格、换行符、制表符
|
||||||
- remove_urls_emails 删除 URL、电子邮件地址
|
- <code>remove_urls_emails</code> 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
|
- <code>enabled</code> (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
|
- <code>segmentation</code> (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
|
- <code>separator</code> 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
|
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -239,7 +239,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<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
|
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
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -252,30 +252,30 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
源文档 ID （选填）
|
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
|
- 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
|
- 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
|
- 当传入 <code>original_document_id</code> 时，代表文档进行更新操作，<code>process_rule</code> 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
|
- 未传入 <code>original_document_id</code> 时，代表文档进行新增操作，<code>process_rule</code> 为必填
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='file' type='multipart/form-data' key='file'>
|
<Property name='file' type='multipart/form-data' key='file'>
|
||||||
需要上传的文件。
|
需要上传的文件。
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
||||||
索引方式
|
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
|
- <code>high_quality</code> 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
|
- <code>economy</code> 经济：使用 Keyword Table Index 的倒排索引进行构建
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
处理规则
|
处理规则
|
||||||
- mode (string) 清洗、分段模式 ，automatic 自动 / custom 自定义。
|
- <code>mode</code> (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）
|
- <code>rules</code> (object) 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
|
- <code>pre_processing_rules</code> (array[object]) 预处理规则
|
||||||
- id (string) 预处理规则的唯一标识符
|
- <code>id</code> (string) 预处理规则的唯一标识符
|
||||||
- 枚举：
|
- 枚举：
|
||||||
- remove_extra_spaces 替换连续空格、换行符、制表符
|
- <code>remove_extra_spaces</code> 替换连续空格、换行符、制表符
|
||||||
- remove_urls_emails 删除 URL、电子邮件地址
|
- <code>remove_urls_emails</code> 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。
|
- <code>enabled</code> (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
|
- <code>segmentation</code> (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
|
- <code>separator</code> 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
|
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -339,7 +339,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<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
|
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
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -359,17 +359,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
处理规则（选填）
|
处理规则（选填）
|
||||||
- mode (string) 清洗、分段模式 ，automatic 自动 / custom 自定义。
|
- <code>mode</code> (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）
|
- <code>rules</code> (object) 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
|
- <code>pre_processing_rules</code> (array[object]) 预处理规则
|
||||||
- id (string) 预处理规则的唯一标识符
|
- <code>id</code> (string) 预处理规则的唯一标识符
|
||||||
- 枚举：
|
- 枚举：
|
||||||
- remove_extra_spaces 替换连续空格、换行符、制表符
|
- <code>remove_extra_spaces</code> 替换连续空格、换行符、制表符
|
||||||
- remove_urls_emails 删除 URL、电子邮件地址
|
- <code>remove_urls_emails</code> 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。
|
- <code>enabled</code> (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
|
- <code>segmentation</code> (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
|
- <code>separator</code> 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
|
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -436,7 +436,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
<Col>
|
<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。
|
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
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -456,17 +456,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
</Property>
|
</Property>
|
||||||
<Property name='process_rule' type='object' key='process_rule'>
|
<Property name='process_rule' type='object' key='process_rule'>
|
||||||
处理规则（选填）
|
处理规则（选填）
|
||||||
- mode (string) 清洗、分段模式 ，automatic 自动 / custom 自定义。
|
- <code>mode</code> (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）
|
- <code>rules</code> (object) 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
|
- <code>pre_processing_rules</code> (array[object]) 预处理规则
|
||||||
- id (string) 预处理规则的唯一标识符
|
- <code>id</code> (string) 预处理规则的唯一标识符
|
||||||
- 枚举：
|
- 枚举：
|
||||||
- remove_extra_spaces 替换连续空格、换行符、制表符
|
- <code>remove_extra_spaces</code> 替换连续空格、换行符、制表符
|
||||||
- remove_urls_emails 删除 URL、电子邮件地址
|
- <code>remove_urls_emails</code> 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
|
- <code>enabled</code> (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
|
- <code>segmentation</code> (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
|
- <code>separator</code> 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
|
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -528,7 +528,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -583,7 +583,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -625,14 +625,14 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
|
|
||||||
### Path Query
|
### Query
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='keyword' type='string' key='keyword'>
|
<Property name='keyword' type='string' key='keyword'>
|
||||||
搜索关键词，可选，目前仅搜索文档名称
|
搜索关键词，可选，目前仅搜索文档名称
|
||||||
|
|
@ -700,7 +700,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
<Col>
|
<Col>
|
||||||
### Path Params
|
### Path
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
数据集 ID
|
数据集 ID
|
||||||
|
|
@ -713,10 +713,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
### Request Body
|
### Request Body
|
||||||
<Properties>
|
<Properties>
|
||||||
<Property name='segments' type='object list' key='segments'>
|
<Property name='segments' type='object list' key='segments'>
|
||||||
segments (object list) 分段内容
|
- <code>content</code> (text) 文本内容/问题内容，必填
|
||||||
- content (text) 文本内容/问题内容，必填
|
- <code>answer</code> (text) 答案内容，非必填，如果数据集的模式为qa模式则传值
|
||||||
- answer(text) 答案内容，非必填，如果数据集的模式为qa模式则传值
|
- <code>keywords</code> (list) 关键字，非必填
|
||||||
- keywords(list) 关键字，非必填
|
|
||||||
</Property>
|
</Property>
|
||||||
</Properties>
|
</Properties>
|
||||||
</Col>
|
</Col>
|
||||||
|
|
@ -779,14 +778,106 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
错误信息
|
<Row>
|
||||||
- **document_indexing**: 文档索引失败
|
<Col>
|
||||||
- **provider_not_initialize**: Embedding 模型未配置
|
### 错误信息
|
||||||
- **not_found**,文档不存在
|
<Properties>
|
||||||
- **dataset_name_duplicate**: 数据集名称重复
|
<Property name='code' type='string' key='code'>
|
||||||
- **provider_quota_exceeded**: 模型额度超过限制
|
返回的错误代码
|
||||||
- **dataset_not_initialized**: 数据集还未初始化
|
</Property>
|
||||||
- **unsupported_file_type**: 不支持的文件类型
|
</Properties>
|
||||||
- 目前只支持：txt, markdown, md, pdf, html, htm, xlsx, docx, csv
|
<Properties>
|
||||||
- **too_many_files**: 文件数量过多，暂时只支持单一文件上传
|
<Property name='status' type='number' key='status'>
|
||||||
- **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
|
返回的错误状态
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
<Properties>
|
||||||
|
<Property name='message' type='string' key='message'>
|
||||||
|
返回的错误信息
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col>
|
||||||
|
<CodeGroup title="Example">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"code": "no_file_uploaded",
|
||||||
|
"message": "Please upload your file.",
|
||||||
|
"status": 400
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
<table className="max-w-auto border-collapse border border-slate-400" style={{ maxWidth: 'none', width: 'auto' }}>
|
||||||
|
<thead style={{ background: '#f9fafc' }}>
|
||||||
|
<tr>
|
||||||
|
<th class="p-2 border border-slate-300">code</th>
|
||||||
|
<th class="p-2 border border-slate-300">status</th>
|
||||||
|
<th class="p-2 border border-slate-300">message</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">no_file_uploaded</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Please upload your file.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">too_many_files</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Only one file is allowed.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">file_too_large</td>
|
||||||
|
<td class="p-2 border border-slate-300">413</td>
|
||||||
|
<td class="p-2 border border-slate-300">File size exceeded.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">unsupported_file_type</td>
|
||||||
|
<td class="p-2 border border-slate-300">415</td>
|
||||||
|
<td class="p-2 border border-slate-300">File type not allowed.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">high_quality_dataset_only</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Current operation only supports 'high-quality' datasets.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">dataset_not_initialized</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The dataset is still being initialized or indexing. Please wait a moment.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">archived_document_immutable</td>
|
||||||
|
<td class="p-2 border border-slate-300">403</td>
|
||||||
|
<td class="p-2 border border-slate-300">The archived document is not editable.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">dataset_name_duplicate</td>
|
||||||
|
<td class="p-2 border border-slate-300">409</td>
|
||||||
|
<td class="p-2 border border-slate-300">The dataset name already exists. Please modify your dataset name.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">invalid_action</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">Invalid action.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">document_already_finished</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The document has been processed. Please refresh the page or go to the document details.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">document_indexing</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The document is being processed and cannot be edited.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td class="p-2 border border-slate-300">invalid_metadata</td>
|
||||||
|
<td class="p-2 border border-slate-300">400</td>
|
||||||
|
<td class="p-2 border border-slate-300">The metadata content is incorrect. Please check and verify.</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
<div class="pb-4" />
|
||||||
|
|
|
||||||
|
|
@ -20,7 +20,7 @@ const LocaleLayout = ({
|
||||||
return (
|
return (
|
||||||
<html lang={locale ?? 'en'} className="h-full">
|
<html lang={locale ?? 'en'} className="h-full">
|
||||||
<body
|
<body
|
||||||
className="h-full"
|
className="h-full select-auto"
|
||||||
data-api-prefix={process.env.NEXT_PUBLIC_API_PREFIX}
|
data-api-prefix={process.env.NEXT_PUBLIC_API_PREFIX}
|
||||||
data-pubic-api-prefix={process.env.NEXT_PUBLIC_PUBLIC_API_PREFIX}
|
data-pubic-api-prefix={process.env.NEXT_PUBLIC_PUBLIC_API_PREFIX}
|
||||||
data-public-edition={process.env.NEXT_PUBLIC_EDITION}
|
data-public-edition={process.env.NEXT_PUBLIC_EDITION}
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user