|
|
@@ -71,7 +71,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
/>
|
|
|
<Row>
|
|
|
<Col>
|
|
|
- ### Path Query
|
|
|
+ ### Query
|
|
|
<Properties>
|
|
|
<Property name='page' type='string' key='page'>
|
|
|
Page number
|
|
|
@@ -136,7 +136,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
<Col>
|
|
|
This api is based on an existing dataset and creates a new document through text based on this dataset.
|
|
|
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -153,22 +153,22 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
</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
|
|
|
+ - <code>high_quality</code> High quality: embedding using embedding model, built as vector database index
|
|
|
+ - <code>economy</code> 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
|
|
|
+ - <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
|
|
+ - <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
|
|
+ - <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
|
|
+ - <code>id</code> (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
|
|
|
+ - <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
|
|
+ - <code>remove_urls_emails</code> Delete URL, email address
|
|
|
+ - <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
|
|
+ - <code>segmentation</code> (object) segmentation rules
|
|
|
+ - <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
|
|
+ - <code>max_tokens</code> Maximum length (token) defaults to 1000
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
</Col>
|
|
|
@@ -238,7 +238,8 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
<Row>
|
|
|
<Col>
|
|
|
This api is based on an existing dataset and creates a new document through a file based on this dataset.
|
|
|
- ### Path Params
|
|
|
+
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -259,22 +260,22 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
</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
|
|
|
+ - <code>high_quality</code> High quality: embedding using embedding model, built as vector database index
|
|
|
+ - <code>economy</code> 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
|
|
|
+ - <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
|
|
+ - <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
|
|
+ - <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
|
|
+ - <code>id</code> (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
|
|
|
+ - <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
|
|
+ - <code>remove_urls_emails</code> Delete URL, email address
|
|
|
+ - <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
|
|
+ - <code>segmentation</code> (object) segmentation rules
|
|
|
+ - <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
|
|
+ - <code>max_tokens</code> Maximum length (token) defaults to 1000
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
</Col>
|
|
|
@@ -338,7 +339,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
<Col>
|
|
|
This api is based on an existing dataset and updates the document through text based on this dataset.
|
|
|
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -358,17 +359,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
</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
|
|
|
+ - <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
|
|
+ - <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
|
|
+ - <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
|
|
+ - <code>id</code> (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
|
|
|
+ - <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
|
|
+ - <code>remove_urls_emails</code> Delete URL, email address
|
|
|
+ - <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
|
|
+ - <code>segmentation</code> (object) segmentation rules
|
|
|
+ - <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
|
|
+ - <code>max_tokens</code> Maximum length (token) defaults to 1000
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
</Col>
|
|
|
@@ -435,7 +436,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
<Col>
|
|
|
This api is based on an existing dataset, and updates documents through files based on this dataset
|
|
|
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -455,17 +456,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
</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
|
|
|
+ - <code>mode</code> (string) Cleaning, segmentation mode, automatic / custom
|
|
|
+ - <code>rules</code> (object) Custom rules (in automatic mode, this field is empty)
|
|
|
+ - <code>pre_processing_rules</code> (array[object]) Preprocessing rules
|
|
|
+ - <code>id</code> (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
|
|
|
+ - <code>remove_extra_spaces</code> Replace consecutive spaces, newlines, tabs
|
|
|
+ - <code>remove_urls_emails</code> Delete URL, email address
|
|
|
+ - <code>enabled</code> (bool) Whether to select this rule or not. If no document ID is passed in, it represents the default value.
|
|
|
+ - <code>segmentation</code> (object) segmentation rules
|
|
|
+ - <code>separator</code> Custom segment identifier, currently only allows one delimiter to be set. Default is \n
|
|
|
+ - <code>max_tokens</code> Maximum length (token) defaults to 1000
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
</Col>
|
|
|
@@ -527,7 +528,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
/>
|
|
|
<Row>
|
|
|
<Col>
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -582,7 +583,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
/>
|
|
|
<Row>
|
|
|
<Col>
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -624,14 +625,14 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
/>
|
|
|
<Row>
|
|
|
<Col>
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
|
|
|
- ### Path Query
|
|
|
+ ### Query
|
|
|
<Properties>
|
|
|
<Property name='keyword' type='string' key='keyword'>
|
|
|
Search keywords, currently only search document names(optional)
|
|
|
@@ -699,7 +700,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
/>
|
|
|
<Row>
|
|
|
<Col>
|
|
|
- ### Path Params
|
|
|
+ ### Params
|
|
|
<Properties>
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
Dataset ID
|
|
|
@@ -712,10 +713,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
### 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)
|
|
|
+ - <code>content</code> (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)
|
|
|
+ - <code>keywords</code> (list) Keywords(optional)
|
|
|
</Property>
|
|
|
</Properties>
|
|
|
</Col>
|
|
|
@@ -778,14 +778,106 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|
|
|
|
|
---
|
|
|
|
|
|
-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
|
|
|
+<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
|
|
|
+ </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" />
|
zxhlyh