|
|
|
@@ -20,17 +20,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</CodeGroup> |
|
|
|
</div> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/document/create_by_text' |
|
|
|
url='/datasets/{dataset_id}/document/create-by-text' |
|
|
|
method='POST' |
|
|
|
title='Create a document from text' |
|
|
|
name='#create_by_text' |
|
|
|
title='Create a Document from Text' |
|
|
|
name='#create-by-text' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
<Col> |
|
|
|
This api is based on an existing Knowledge and creates a new document through text based on this Knowledge. |
|
|
|
This API is based on an existing knowledge and creates a new document through text based on this knowledge. |
|
|
|
|
|
|
|
### Params |
|
|
|
<Properties> |
|
|
|
@@ -50,7 +50,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<Property name='indexing_technique' type='string' key='indexing_technique'> |
|
|
|
Index mode |
|
|
|
- <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 |
|
|
|
- <code>economy</code> Economy: Build using inverted index of keyword table index |
|
|
|
</Property> |
|
|
|
<Property name='process_rule' type='object' key='process_rule'> |
|
|
|
Processing rules |
|
|
|
@@ -62,7 +62,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
- <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>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> |
|
|
|
@@ -72,11 +72,11 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets/{dataset_id}/document/create_by_text" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "text","text": "text","indexing_technique": "high_quality","process_rule": {"mode": "automatic"}}'`} |
|
|
|
label="/datasets/{dataset_id}/document/create-by-text" |
|
|
|
targetCode={`curl --location --request POST '${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 '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_text' \ |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-text' \ |
|
|
|
--header 'Authorization: Bearer {api_key}' \ |
|
|
|
--header 'Content-Type: application/json' \ |
|
|
|
--data-raw '{ |
|
|
|
@@ -123,17 +123,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/document/create_by_file' |
|
|
|
url='/datasets/{dataset_id}/document/create-by-file' |
|
|
|
method='POST' |
|
|
|
title='Create documents from files' |
|
|
|
name='#create_by_file' |
|
|
|
title='Create a Document from a File' |
|
|
|
name='#create-by-file' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
<Col> |
|
|
|
This api is based on an existing Knowledge and creates a new document through a file based on this Knowledge. |
|
|
|
This API is based on an existing knowledge and creates a new document through a file based on this knowledge. |
|
|
|
|
|
|
|
### Params |
|
|
|
<Properties> |
|
|
|
@@ -145,17 +145,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
### Request Body |
|
|
|
<Properties> |
|
|
|
<Property name='data' type='multipart/form-data json string' key='data'> |
|
|
|
- original_document_id Source document ID (optional) |
|
|
|
- <code>original_document_id</code> 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 default |
|
|
|
- When original_document_id is not passed in, the new operation is performed on behalf of the document, and process_rule is required |
|
|
|
|
|
|
|
- indexing_technique Index mode |
|
|
|
- <code>indexing_technique</code> Index mode |
|
|
|
- <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 |
|
|
|
- <code>economy</code> Economy: Build using inverted index of keyword table index |
|
|
|
|
|
|
|
- process_rule Processing rules |
|
|
|
- <code>process_rule</code> Processing rules |
|
|
|
- <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 |
|
|
|
@@ -164,7 +164,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
- <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>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> |
|
|
|
@@ -177,11 +177,11 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets/{dataset_id}/document/create_by_file" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`} |
|
|
|
label="/datasets/{dataset_id}/document/create-by-file" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"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 --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_file' \ |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/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"' |
|
|
|
@@ -221,12 +221,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets' |
|
|
|
method='POST' |
|
|
|
title='Create an empty Knowledge' |
|
|
|
title='Create an Empty Knowledge Base' |
|
|
|
name='#create_empty_dataset' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -240,9 +240,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
Knowledge description (optional) |
|
|
|
</Property> |
|
|
|
<Property name='indexing_technique' type='string' key='indexing_technique'> |
|
|
|
Index Technique (optional) |
|
|
|
- <code>high_quality</code> high_quality |
|
|
|
- <code>economy</code> economy |
|
|
|
Index technique (optional) |
|
|
|
- <code>high_quality</code> High quality |
|
|
|
- <code>economy</code> Economy |
|
|
|
</Property> |
|
|
|
<Property name='permission' type='string' key='permission'> |
|
|
|
Permission |
|
|
|
@@ -252,21 +252,21 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Property> |
|
|
|
<Property name='provider' type='string' key='provider'> |
|
|
|
Provider (optional, default: vendor) |
|
|
|
- <code>vendor</code> vendor |
|
|
|
- <code>external</code> external knowledge |
|
|
|
- <code>vendor</code> Vendor |
|
|
|
- <code>external</code> External knowledge |
|
|
|
</Property> |
|
|
|
<Property name='external_knowledge_api_id' type='str' key='external_knowledge_api_id'> |
|
|
|
External Knowledge api id (optional) |
|
|
|
External knowledge API ID (optional) |
|
|
|
</Property> |
|
|
|
<Property name='external_knowledge_id' type='str' key='external_knowledge_id'> |
|
|
|
External Knowledge id (optional) |
|
|
|
External knowledge ID (optional) |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
<Col sticky> |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name", "permission": "only_me"}'`} |
|
|
|
> |
|
|
|
@@ -306,12 +306,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets' |
|
|
|
method='GET' |
|
|
|
title='Knowledge list' |
|
|
|
title='Get Knowledge Base List' |
|
|
|
name='#dataset_list' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -327,9 +327,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
<Col sticky> |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets" |
|
|
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`} |
|
|
|
> |
|
|
|
@@ -369,12 +369,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}' |
|
|
|
method='DELETE' |
|
|
|
title='Delete knowledge' |
|
|
|
title='Delete a Knowledge Base' |
|
|
|
name='#delete_dataset' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -406,17 +406,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/update_by_text' |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/update-by-text' |
|
|
|
method='POST' |
|
|
|
title='Update document via text' |
|
|
|
name='#update_by_text' |
|
|
|
title='Update a Document with Text' |
|
|
|
name='#update-by-text' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
<Col> |
|
|
|
This api is based on an existing Knowledge and updates the document through text based on this Knowledge. |
|
|
|
This API is based on an existing knowledge and updates the document through text based on this knowledge. |
|
|
|
|
|
|
|
### Params |
|
|
|
<Properties> |
|
|
|
@@ -446,7 +446,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
- <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>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> |
|
|
|
@@ -456,11 +456,11 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets/{dataset_id}/documents/{document_id}/update_by_text" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name","text": "text"}'`} |
|
|
|
label="/datasets/{dataset_id}/documents/{document_id}/update-by-text" |
|
|
|
targetCode={`curl --location --request POST '${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 '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_text' \ |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-text' \ |
|
|
|
--header 'Authorization: Bearer {api_key}' \ |
|
|
|
--header 'Content-Type: application/json' \ |
|
|
|
--data-raw '{ |
|
|
|
@@ -503,17 +503,17 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/update_by_file' |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/update-by-file' |
|
|
|
method='POST' |
|
|
|
title='Update a document from a file' |
|
|
|
name='#update_by_file' |
|
|
|
title='Update a Document with a File' |
|
|
|
name='#update-by-file' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
<Col> |
|
|
|
This api is based on an existing Knowledge, and updates documents through files based on this Knowledge |
|
|
|
This API is based on an existing knowledge, and updates documents through files based on this knowledge |
|
|
|
|
|
|
|
### Params |
|
|
|
<Properties> |
|
|
|
@@ -543,7 +543,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
- <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>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> |
|
|
|
@@ -553,11 +553,11 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets/{dataset_id}/documents/{document_id}/update_by_file" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`} |
|
|
|
label="/datasets/{dataset_id}/documents/{document_id}/update-by-file" |
|
|
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-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 --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update_by_file' \ |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-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"' |
|
|
|
@@ -597,12 +597,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{batch}/indexing-status' |
|
|
|
method='GET' |
|
|
|
title='Get document embedding status (progress)' |
|
|
|
title='Get Document Embedding Status (Progress)' |
|
|
|
name='#indexing_status' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -652,12 +652,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}' |
|
|
|
method='DELETE' |
|
|
|
title='Delete document' |
|
|
|
title='Delete a Document' |
|
|
|
name='#delete_document' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -694,12 +694,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents' |
|
|
|
method='GET' |
|
|
|
title='Knowledge document list' |
|
|
|
title='Get the Document List of a Knowledge Base' |
|
|
|
name='#dataset_document_list' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -714,13 +714,13 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
### Query |
|
|
|
<Properties> |
|
|
|
<Property name='keyword' type='string' key='keyword'> |
|
|
|
Search keywords, currently only search document names(optional) |
|
|
|
Search keywords, currently only search document names (optional) |
|
|
|
</Property> |
|
|
|
<Property name='page' type='string' key='page'> |
|
|
|
Page number(optional) |
|
|
|
Page number (optional) |
|
|
|
</Property> |
|
|
|
<Property name='limit' type='string' key='limit'> |
|
|
|
Number of items returned, default 20, range 1-100(optional) |
|
|
|
Number of items returned, default 20, range 1-100 (optional) |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
@@ -769,12 +769,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/segments' |
|
|
|
method='POST' |
|
|
|
title='Add segment' |
|
|
|
title='Add Chunks to a Document' |
|
|
|
name='#create_new_segment' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -792,9 +792,9 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
### Request Body |
|
|
|
<Properties> |
|
|
|
<Property name='segments' type='object list' key='segments'> |
|
|
|
- <code>content</code> (text) Text content/question content, required |
|
|
|
- <code>answer</code> (text) Answer content, if the mode of the Knowledge is qa mode, pass the value(optional) |
|
|
|
- <code>keywords</code> (list) Keywords(optional) |
|
|
|
- <code>content</code> (text) Text content / question content, required |
|
|
|
- <code>answer</code> (text) Answer content, if the mode of the knowledge is Q&A mode, pass the value (optional) |
|
|
|
- <code>keywords</code> (list) Keywords (optional) |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
@@ -855,12 +855,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/segments' |
|
|
|
method='GET' |
|
|
|
title='get documents segments' |
|
|
|
title='Get Chunks from a Document' |
|
|
|
name='#get_segment' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -878,10 +878,10 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
### Query |
|
|
|
<Properties> |
|
|
|
<Property name='keyword' type='string' key='keyword'> |
|
|
|
keyword，choosable |
|
|
|
Keyword (optional) |
|
|
|
</Property> |
|
|
|
<Property name='status' type='string' key='status'> |
|
|
|
Search status，completed |
|
|
|
Search status, completed |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
@@ -933,12 +933,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' |
|
|
|
method='DELETE' |
|
|
|
title='delete document segment' |
|
|
|
title='Delete a Chunk in a Document' |
|
|
|
name='#delete_segment' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -979,12 +979,12 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' |
|
|
|
method='POST' |
|
|
|
title='update document segment' |
|
|
|
title='Update a Chunk in a Document ' |
|
|
|
name='#update_segment' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
@@ -1005,10 +1005,10 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
### Request Body |
|
|
|
<Properties> |
|
|
|
<Property name='segment' type='object' key='segment'> |
|
|
|
- <code>content</code> (text) text content/question content，required |
|
|
|
- <code>answer</code> (text) Answer content, not required, passed if the Knowledge is in qa mode |
|
|
|
- <code>keywords</code> (list) keyword, not required |
|
|
|
- <code>enabled</code> (bool) false/true, not required |
|
|
|
- <code>content</code> (text) Text content / question content, required |
|
|
|
- <code>answer</code> (text) Answer content, passed if the knowledge is in Q&A mode (optional) |
|
|
|
- <code>keywords</code> (list) Keyword (optional) |
|
|
|
- <code>enabled</code> (bool) False / true (optional) |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
</Col> |
|
|
|
@@ -1067,41 +1067,41 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Heading |
|
|
|
url='/datasets/{dataset_id}/hit-testing' |
|
|
|
url='/datasets/{dataset_id}/retrieve' |
|
|
|
method='POST' |
|
|
|
title='Dataset hit testing' |
|
|
|
name='#dataset_hit_testing' |
|
|
|
title='Retrieve Chunks from a Knowledge Base' |
|
|
|
name='#dataset_retrieval' |
|
|
|
/> |
|
|
|
<Row> |
|
|
|
<Col> |
|
|
|
### Path |
|
|
|
<Properties> |
|
|
|
<Property name='dataset_id' type='string' key='dataset_id'> |
|
|
|
Dataset ID |
|
|
|
Knowledge ID |
|
|
|
</Property> |
|
|
|
</Properties> |
|
|
|
|
|
|
|
### Request Body |
|
|
|
<Properties> |
|
|
|
<Property name='query' type='string' key='query'> |
|
|
|
retrieval keywordc |
|
|
|
Query keyword |
|
|
|
</Property> |
|
|
|
<Property name='retrieval_model' type='object' key='retrieval_model'> |
|
|
|
retrieval keyword(Optional, if not filled, it will be recalled according to the default method) |
|
|
|
Retrieval model (optional, if not filled, it will be recalled according to the default method) |
|
|
|
- <code>search_method</code> (text) Search method: One of the following four keywords is required |
|
|
|
- <code>keyword_search</code> Keyword search |
|
|
|
- <code>semantic_search</code> Semantic search |
|
|
|
- <code>full_text_search</code> Full-text search |
|
|
|
- <code>hybrid_search</code> Hybrid search |
|
|
|
- <code>reranking_enable</code> (bool) Whether to enable reranking, optional, required if the search mode is semantic_search or hybrid_search |
|
|
|
- <code>reranking_mode</code> (object) Rerank model configuration, optional, required if reranking is enabled |
|
|
|
- <code>reranking_enable</code> (bool) Whether to enable reranking, required if the search mode is semantic_search or hybrid_search (optional) |
|
|
|
- <code>reranking_mode</code> (object) Rerank model configuration, required if reranking is enabled |
|
|
|
- <code>reranking_provider_name</code> (string) Rerank model provider |
|
|
|
- <code>reranking_model_name</code> (string) Rerank model name |
|
|
|
- <code>weights</code> (double) Semantic search weight setting in hybrid search mode |
|
|
|
- <code>top_k</code> (integer) Number of results to return, optional |
|
|
|
- <code>top_k</code> (integer) Number of results to return (optional) |
|
|
|
- <code>score_threshold_enabled</code> (bool) Whether to enable score threshold |
|
|
|
- <code>score_threshold</code> (double) Score threshold |
|
|
|
</Property> |
|
|
|
@@ -1114,26 +1114,26 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
<CodeGroup |
|
|
|
title="Request" |
|
|
|
tag="POST" |
|
|
|
label="/datasets/{dataset_id}/hit-testing" |
|
|
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/hit-testing' \\\n--header 'Authorization: Bearer {api_key}'\\\n--header 'Content-Type: application/json'\\\n--data-raw '{ |
|
|
|
"query": "test", |
|
|
|
"retrieval_model": { |
|
|
|
"search_method": "keyword_search", |
|
|
|
"reranking_enable": false, |
|
|
|
"reranking_mode": null, |
|
|
|
"reranking_model": { |
|
|
|
"reranking_provider_name": "", |
|
|
|
"reranking_model_name": "" |
|
|
|
}, |
|
|
|
"weights": null, |
|
|
|
"top_k": 1, |
|
|
|
"score_threshold_enabled": false, |
|
|
|
"score_threshold": null |
|
|
|
} |
|
|
|
}'`} |
|
|
|
label="/datasets/{dataset_id}/retrieve" |
|
|
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/retrieve' \\\n--header 'Authorization: Bearer {api_key}'\\\n--header 'Content-Type: application/json'\\\n--data-raw '{ |
|
|
|
"query": "test", |
|
|
|
"retrieval_model": { |
|
|
|
"search_method": "keyword_search", |
|
|
|
"reranking_enable": false, |
|
|
|
"reranking_mode": null, |
|
|
|
"reranking_model": { |
|
|
|
"reranking_provider_name": "", |
|
|
|
"reranking_model_name": "" |
|
|
|
}, |
|
|
|
"weights": null, |
|
|
|
"top_k": 1, |
|
|
|
"score_threshold_enabled": false, |
|
|
|
"score_threshold": null |
|
|
|
} |
|
|
|
}'`} |
|
|
|
> |
|
|
|
```bash {{ title: 'cURL' }} |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/hit-testing' \ |
|
|
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/retrieve' \ |
|
|
|
--header 'Authorization: Bearer {api_key}' \ |
|
|
|
--header 'Content-Type: application/json' \ |
|
|
|
--data-raw '{ |
|
|
|
@@ -1212,7 +1212,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from |
|
|
|
</Col> |
|
|
|
</Row> |
|
|
|
|
|
|
|
--- |
|
|
|
<hr className='ml-0 mr-0' /> |
|
|
|
|
|
|
|
<Row> |
|
|
|
<Col> |
Jyong
před 1 rokem