|
|
|
@@ -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
před 2 roky