mirror of
https://github.com/langgenius/dify.git
synced 2024-11-16 11:42:29 +08:00
Feat/update knowledge api url (#10102)
Co-authored-by: nite-knite <nkCoding@gmail.com>
This commit is contained in:
Jyong
GitHub
parent
11ca1bec0b
commit
ce260f79d2
|
|
@ -331,10 +331,26 @@ class DocumentIndexingStatusApi(DatasetApiResource):
|
|||
return data
|
||||
|
||||
|
||||
api.add_resource(DocumentAddByTextApi, "/datasets/<uuid:dataset_id>/document/create_by_text")
|
||||
api.add_resource(DocumentAddByFileApi, "/datasets/<uuid:dataset_id>/document/create_by_file")
|
||||
api.add_resource(DocumentUpdateByTextApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text")
|
||||
api.add_resource(DocumentUpdateByFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file")
|
||||
api.add_resource(
|
||||
DocumentAddByTextApi,
|
||||
"/datasets/<uuid:dataset_id>/document/create_by_text",
|
||||
"/datasets/<uuid:dataset_id>/document/create-by-text",
|
||||
)
|
||||
api.add_resource(
|
||||
DocumentAddByFileApi,
|
||||
"/datasets/<uuid:dataset_id>/document/create_by_file",
|
||||
"/datasets/<uuid:dataset_id>/document/create-by-file",
|
||||
)
|
||||
api.add_resource(
|
||||
DocumentUpdateByTextApi,
|
||||
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text",
|
||||
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
|
||||
)
|
||||
api.add_resource(
|
||||
DocumentUpdateByFileApi,
|
||||
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file",
|
||||
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-file",
|
||||
)
|
||||
api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
|
||||
api.add_resource(DocumentListApi, "/datasets/<uuid:dataset_id>/documents")
|
||||
api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status")
|
||||
|
|
|
|||
|
|
@ -14,4 +14,4 @@ class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
|
|||
return self.perform_hit_testing(dataset, args)
|
||||
|
||||
|
||||
api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
|
||||
api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing", "/datasets/<uuid:dataset_id>/retrieve")
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
'use client'
|
||||
|
||||
import type { FC } from 'react'
|
||||
import { type FC, useEffect } from 'react'
|
||||
import { useContext } from 'use-context-selector'
|
||||
import TemplateEn from './template/template.en.mdx'
|
||||
import TemplateZh from './template/template.zh.mdx'
|
||||
|
|
@ -14,6 +14,13 @@ const Doc: FC<DocProps> = ({
|
|||
apiBaseUrl,
|
||||
}) => {
|
||||
const { locale } = useContext(I18n)
|
||||
|
||||
useEffect(() => {
|
||||
const hash = location.hash
|
||||
if (hash)
|
||||
document.querySelector(hash)?.scrollIntoView()
|
||||
}, [])
|
||||
|
||||
return (
|
||||
<article className='mx-1 px-4 sm:mx-12 pt-16 bg-white rounded-t-xl prose prose-xl'>
|
||||
{
|
||||
|
|
|
|||
|
|
@ -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>
|
||||
|
|
|
|||
|
|
@ -20,13 +20,13 @@ 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='通过文本创建文档'
|
||||
name='#create_by_text'
|
||||
name='#create-by-text'
|
||||
/>
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
@ -50,7 +50,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
||||
索引方式
|
||||
- <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
|
||||
- <code>economy</code> 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 name='process_rule' type='object' key='process_rule'>
|
||||
处理规则
|
||||
|
|
@ -64,7 +64,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
- <code>enabled</code> (bool) 是否选中该规则，不传入文档 ID 时代表默认值
|
||||
- <code>segmentation</code> (object) 分段规则
|
||||
- <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
|
||||
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||
- <code>max_tokens</code> 最大长度（token）默认为 1000
|
||||
</Property>
|
||||
</Properties>
|
||||
</Col>
|
||||
|
|
@ -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 --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create_by_text' \
|
||||
curl --location --request --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-text' \
|
||||
--header 'Authorization: Bearer {api_key}' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
|
|
@ -123,13 +123,13 @@ 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='通过文件创建文档 '
|
||||
name='#create_by_file'
|
||||
name='#create-by-file'
|
||||
/>
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
@ -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 源文档 ID （选填）
|
||||
- <code>original_document_id</code> 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
|
||||
- 源文档不可为归档的文档
|
||||
- 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 <code>original_document_id</code> 时，代表文档进行新增操作，<code>process_rule</code> 为必填
|
||||
|
||||
- indexing_technique 索引方式
|
||||
- <code>indexing_technique</code> 索引方式
|
||||
- <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
|
||||
- <code>economy</code> 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
|
||||
|
||||
- process_rule 处理规则
|
||||
- <code>process_rule</code> 处理规则
|
||||
- <code>mode</code> (string) 清洗、分段模式 ，automatic 自动 / custom 自定义
|
||||
- <code>rules</code> (object) 自定义规则（自动模式下，该字段为空）
|
||||
- <code>pre_processing_rules</code> (array[object]) 预处理规则
|
||||
|
|
@ -166,7 +166,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
- <code>enabled</code> (bool) 是否选中该规则，不传入文档 ID 时代表默认值
|
||||
- <code>segmentation</code> (object) 分段规则
|
||||
- <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
|
||||
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||
- <code>max_tokens</code> 最大长度（token）默认为 1000
|
||||
</Property>
|
||||
<Property name='file' type='multipart/form-data' key='file'>
|
||||
需要上传的文件。
|
||||
|
|
@ -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"'
|
||||
|
|
@ -221,7 +221,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Col>
|
||||
</Row>
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Heading
|
||||
url='/datasets'
|
||||
|
|
@ -245,13 +245,13 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
- <code>economy</code> 经济
|
||||
</Property>
|
||||
<Property name='permission' type='string' key='permission'>
|
||||
权限（选填，默认only_me）
|
||||
权限（选填，默认 only_me）
|
||||
- <code>only_me</code> 仅自己
|
||||
- <code>all_team_members</code> 所有团队成员
|
||||
- <code>partial_members</code> 部分团队成员
|
||||
</Property>
|
||||
<Property name='provider' type='string' key='provider'>
|
||||
provider，（选填，默认 vendor）
|
||||
Provider（选填，默认 vendor）
|
||||
- <code>vendor</code> 上传文件
|
||||
- <code>external</code> 外部知识库
|
||||
</Property>
|
||||
|
|
@ -264,9 +264,9 @@ 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 POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name", "permission": "only_me"}'`}
|
||||
>
|
||||
|
|
@ -306,7 +306,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Col>
|
||||
</Row>
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Heading
|
||||
url='/datasets'
|
||||
|
|
@ -369,7 +369,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Col>
|
||||
</Row>
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Heading
|
||||
url='/datasets/{dataset_id}'
|
||||
|
|
@ -406,13 +406,13 @@ 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='通过文本更新文档 '
|
||||
name='#update_by_text'
|
||||
name='#update-by-text'
|
||||
/>
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
@ -431,7 +431,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
### Request Body
|
||||
<Properties>
|
||||
<Property name='name' type='string' key='name'>
|
||||
文档名称 （选填）
|
||||
文档名称（选填）
|
||||
</Property>
|
||||
<Property name='text' type='string' key='text'>
|
||||
文档内容（选填）
|
||||
|
|
@ -448,7 +448,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
- <code>enabled</code> (bool) 是否选中该规则，不传入文档 ID 时代表默认值
|
||||
- <code>segmentation</code> (object) 分段规则
|
||||
- <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
|
||||
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||
- <code>max_tokens</code> 最大长度（token）默认为 1000
|
||||
</Property>
|
||||
</Properties>
|
||||
</Col>
|
||||
|
|
@ -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 '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-text' \
|
||||
--header 'Authorization: Bearer {api_key}' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
|
|
@ -503,13 +503,13 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Col>
|
||||
</Row>
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Heading
|
||||
url='/datasets/{dataset_id}/documents/{document_id}/update_by_file'
|
||||
url='/datasets/{dataset_id}/documents/{document_id}/update-by-file'
|
||||
method='POST'
|
||||
title='通过文件更新文档 '
|
||||
name='#update_by_file'
|
||||
name='#update-by-file'
|
||||
/>
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
@ -528,7 +528,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
### Request Body
|
||||
<Properties>
|
||||
<Property name='name' type='string' key='name'>
|
||||
文档名称 （选填）
|
||||
文档名称（选填）
|
||||
</Property>
|
||||
<Property name='file' type='multipart/form-data' key='file'>
|
||||
需要上传的文件
|
||||
|
|
@ -545,7 +545,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
- <code>enabled</code> (bool) 是否选中该规则，不传入文档 ID 时代表默认值
|
||||
- <code>segmentation</code> (object) 分段规则
|
||||
- <code>separator</code> 自定义分段标识符，目前仅允许设置一个分隔符。默认为 \n
|
||||
- <code>max_tokens</code> 最大长度 (token) 默认为 1000
|
||||
- <code>max_tokens</code> 最大长度（token）默认为 1000
|
||||
</Property>
|
||||
</Properties>
|
||||
</Col>
|
||||
|
|
@ -553,11 +553,11 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
<CodeGroup
|
||||
title="Request"
|
||||
tag="POST"
|
||||
label="/datasets/{dataset_id}/documents/{document_id}/update_by_file"
|
||||
targetCode={`curl --location --request POST '${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"'
|
||||
|
|
@ -597,7 +597,7 @@ 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'
|
||||
|
|
@ -652,7 +652,7 @@ 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}'
|
||||
|
|
@ -694,7 +694,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Col>
|
||||
</Row>
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Heading
|
||||
url='/datasets/{dataset_id}/documents'
|
||||
|
|
@ -769,7 +769,7 @@ 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'
|
||||
|
|
@ -793,7 +793,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
<Properties>
|
||||
<Property name='segments' type='object list' key='segments'>
|
||||
- <code>content</code> (text) 文本内容/问题内容，必填
|
||||
- <code>answer</code> (text) 答案内容，非必填，如果知识库的模式为qa模式则传值
|
||||
- <code>answer</code> (text) 答案内容，非必填，如果知识库的模式为 Q&A 模式则传值
|
||||
- <code>keywords</code> (list) 关键字，非必填
|
||||
</Property>
|
||||
</Properties>
|
||||
|
|
@ -855,7 +855,7 @@ 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'
|
||||
|
|
@ -933,7 +933,7 @@ 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}'
|
||||
|
|
@ -979,7 +979,7 @@ 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}'
|
||||
|
|
@ -1006,7 +1006,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
<Properties>
|
||||
<Property name='segment' type='object' key='segment'>
|
||||
- <code>content</code> (text) 文本内容/问题内容，必填
|
||||
- <code>answer</code> (text) 答案内容，非必填，如果知识库的模式为qa模式则传值
|
||||
- <code>answer</code> (text) 答案内容，非必填，如果知识库的模式为 Q&A 模式则传值
|
||||
- <code>keywords</code> (list) 关键字，非必填
|
||||
- <code>enabled</code> (bool) false/true，非必填
|
||||
</Property>
|
||||
|
|
@ -1068,13 +1068,13 @@ 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='知识库召回测试'
|
||||
name='#dataset_hit_testing'
|
||||
title='检索知识库'
|
||||
name='#dataset_retrieval'
|
||||
/>
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
@ -1088,23 +1088,23 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
### Request Body
|
||||
<Properties>
|
||||
<Property name='query' type='string' key='query'>
|
||||
召回关键词
|
||||
检索关键词
|
||||
</Property>
|
||||
<Property name='retrieval_model' type='object' key='retrieval_model'>
|
||||
召回参数(选填，如不填，按照默认方式召回)
|
||||
检索参数（选填，如不填，按照默认方式召回）
|
||||
- <code>search_method</code> (text) 检索方法：以下三个关键字之一，必填
|
||||
- <code>keyword_search</code> 关键字检索
|
||||
- <code>semantic_search</code> 语义检索
|
||||
- <code>full_text_search</code> 全文检索
|
||||
- <code>hybrid_search</code> 混合检索
|
||||
- <code>reranking_enable</code> (bool) 是否启用 Reranking，非必填，如果检索模式为semantic_search模式或者hybrid_search则传值
|
||||
- <code>reranking_enable</code> (bool) 是否启用 Reranking，非必填，如果检索模式为 semantic_search 模式或者 hybrid_search 则传值
|
||||
- <code>reranking_mode</code> (object) Rerank模型配置，非必填，如果启用了 reranking 则传值
|
||||
- <code>reranking_provider_name</code> (string) Rerank 模型提供商
|
||||
- <code>reranking_model_name</code> (string) Rerank 模型名称
|
||||
- <code>weights</code> (double) 混合检索模式下语意检索的权重设置
|
||||
- <code>top_k</code> (integer) 返回结果数量，非必填
|
||||
- <code>score_threshold_enabled</code> (bool) 是否开启Score阈值
|
||||
- <code>score_threshold</code> (double) Score阈值
|
||||
- <code>score_threshold_enabled</code> (bool) 是否开启 score 阈值
|
||||
- <code>score_threshold</code> (double) Score 阈值
|
||||
</Property>
|
||||
<Property name='external_retrieval_model' type='object' key='external_retrieval_model'>
|
||||
未启用字段
|
||||
|
|
@ -1115,26 +1115,26 @@ 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 '{
|
||||
|
|
@ -1214,7 +1214,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
|
|||
</Row>
|
||||
|
||||
|
||||
---
|
||||
<hr className='ml-0 mr-0' />
|
||||
|
||||
<Row>
|
||||
<Col>
|
||||
|
|
|
|||
|
|
@ -39,6 +39,7 @@ export const Heading = function H2({
|
|||
}
|
||||
return (
|
||||
<>
|
||||
<span id={name?.replace(/^#/, '')} className='relative -top-28' />
|
||||
<div className="flex items-center gap-x-3" >
|
||||
<span className={`font-mono text-[0.625rem] font-semibold leading-6 rounded-lg px-1.5 ring-1 ring-inset ${style}`}>{method}</span>
|
||||
{/* <span className="h-0.5 w-0.5 rounded-full bg-zinc-300 dark:bg-zinc-600"></span> */}
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user