import { CodeGroup } from '@/app/components/develop/code.tsx'
|
import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstruction, Paragraph } from '@/app/components/develop/md.tsx'
|
|
# Knowledge API
|
|
<div>
|
### Authentication
|
|
Service API of Dify authenticates using an `API-Key`.
|
|
It is suggested that developers store the `API-Key` in the backend instead of sharing or storing it in the client side to avoid the leakage of the `API-Key`, which may lead to property loss.
|
|
All API requests should include your `API-Key` in the **`Authorization`** HTTP Header, as shown below:
|
|
<CodeGroup title="Code">
|
```javascript
|
Authorization: Bearer {API_KEY}
|
|
```
|
</CodeGroup>
|
</div>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/document/create-by-text'
|
method='POST'
|
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.
|
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
</Properties>
|
|
### Request Body
|
<Properties>
|
<Property name='name' type='string' key='name'>
|
Document name
|
</Property>
|
<Property name='text' type='string' key='text'>
|
Document content
|
</Property>
|
<Property name='doc_type' type='string' key='doc_type'>
|
Type of document (optional):
|
- <code>book</code> Book
|
- <code>web_page</code> Web page
|
- <code>paper</code> Academic paper/article
|
- <code>social_media_post</code> Social media post
|
- <code>wikipedia_entry</code> Wikipedia entry
|
- <code>personal_document</code> Personal document
|
- <code>business_document</code> Business document
|
- <code>im_chat_log</code> Chat log
|
- <code>synced_from_notion</code> Notion document
|
- <code>synced_from_github</code> GitHub document
|
- <code>others</code> Other document types
|
</Property>
|
<Property name='doc_metadata' type='object' key='doc_metadata'>
|
Document metadata (required if doc_type is provided). Fields vary by doc_type:
|
For <code>book</code>:
|
- <code>title</code> Book title
|
- <code>language</code> Book language
|
- <code>author</code> Book author
|
- <code>publisher</code> Publisher name
|
- <code>publication_date</code> Publication date
|
- <code>isbn</code> ISBN number
|
- <code>category</code> Book category
|
|
For <code>web_page</code>:
|
- <code>title</code> Page title
|
- <code>url</code> Page URL
|
- <code>language</code> Page language
|
- <code>publish_date</code> Publish date
|
- <code>author/publisher</code> Author or publisher
|
- <code>topic/keywords</code> Topic or keywords
|
- <code>description</code> Page description
|
|
Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
|
|
For doc_type "others", any valid JSON object is accepted
|
</Property>
|
<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
|
</Property>
|
<Property name='doc_form' type='string' key='doc_form'>
|
Format of indexed content
|
- <code>text_model</code> Text documents are directly embedded; `economy` mode defaults to using this form
|
- <code>hierarchical_model</code> Parent-child mode
|
- <code>qa_model</code> Q&A Mode: Generates Q&A pairs for segmented documents and then embeds the questions
|
</Property>
|
<Property name='doc_language' type='string' key='doc_language'>
|
In Q&A mode, specify the language of the document, for example: <code>English</code>, <code>Chinese</code>
|
</Property>
|
<Property name='process_rule' type='object' key='process_rule'>
|
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
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
- enumerate
|
- <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
|
- <code>parent_mode</code> Retrieval mode of parent chunks: <code>full-doc</code> full text retrieval / <code>paragraph</code> paragraph retrieval
|
- <code>subchunk_segmentation</code> (object) Child chunk rules
|
- <code>separator</code> Segmentation identifier. Currently, only one delimiter is allowed. The default is <code>***</code>
|
- <code>max_tokens</code> The maximum length (tokens) must be validated to be shorter than the length of the parent chunk
|
- <code>chunk_overlap</code> Define the overlap between adjacent chunks (optional)
|
</Property>
|
<PropertyInstruction>When no parameters are set for the knowledge base, the first upload requires the following parameters to be provided; if not provided, the default parameters will be used.</PropertyInstruction>
|
<Property name='retrieval_model' type='object' key='retrieval_model'>
|
Retrieval model
|
- <code>search_method</code> (string) Search method
|
- <code>hybrid_search</code> Hybrid search
|
- <code>semantic_search</code> Semantic search
|
- <code>full_text_search</code> Full-text search
|
- <code>reranking_enable</code> (bool) Whether to enable reranking
|
- <code>reranking_mode</code> (object) Rerank model configuration
|
- <code>reranking_provider_name</code> (string) Rerank model provider
|
- <code>reranking_model_name</code> (string) Rerank model name
|
- <code>top_k</code> (int) Number of results to return
|
- <code>score_threshold_enabled</code> (bool) Whether to enable score threshold
|
- <code>score_threshold</code> (float) Score threshold
|
</Property>
|
<Property name='embedding_model' type='string' key='embedding_model'>
|
Embedding model name
|
</Property>
|
<Property name='embedding_model_provider' type='string' key='embedding_model_provider'>
|
Embedding model provider
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/document/create-by-text"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "text","text": "text","indexing_technique": "high_quality","process_rule": {"mode": "automatic"}}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-text' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json' \
|
--data-raw '{
|
"name": "text",
|
"text": "text",
|
"indexing_technique": "high_quality",
|
"process_rule": {
|
"mode": "automatic"
|
}
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"document": {
|
"id": "",
|
"position": 1,
|
"data_source_type": "upload_file",
|
"data_source_info": {
|
"upload_file_id": ""
|
},
|
"dataset_process_rule_id": "",
|
"name": "text.txt",
|
"created_from": "api",
|
"created_by": "",
|
"created_at": 1695690280,
|
"tokens": 0,
|
"indexing_status": "waiting",
|
"error": null,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"archived": false,
|
"display_status": "queuing",
|
"word_count": 0,
|
"hit_count": 0,
|
"doc_form": "text_model"
|
},
|
"batch": ""
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/document/create-by-file'
|
method='POST'
|
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.
|
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
</Properties>
|
|
### Request Body
|
<Properties>
|
<Property name='data' type='multipart/form-data json string' key='data'>
|
- <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
|
|
- <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>doc_form</code> Format of indexed content
|
- <code>text_model</code> Text documents are directly embedded; `economy` mode defaults to using this form
|
- <code>hierarchical_model</code> Parent-child mode
|
- <code>qa_model</code> Q&A Mode: Generates Q&A pairs for segmented documents and then embeds the questions
|
|
- <code>doc_type</code> Type of document (optional)
|
- <code>book</code> Book
|
Document records a book or publication
|
- <code>web_page</code> Web page
|
Document records web page content
|
- <code>paper</code> Academic paper/article
|
Document records academic paper or research article
|
- <code>social_media_post</code> Social media post
|
Content from social media posts
|
- <code>wikipedia_entry</code> Wikipedia entry
|
Content from Wikipedia entries
|
- <code>personal_document</code> Personal document
|
Documents related to personal content
|
- <code>business_document</code> Business document
|
Documents related to business content
|
- <code>im_chat_log</code> Chat log
|
Records of instant messaging chats
|
- <code>synced_from_notion</code> Notion document
|
Documents synchronized from Notion
|
- <code>synced_from_github</code> GitHub document
|
Documents synchronized from GitHub
|
- <code>others</code> Other document types
|
Other document types not listed above
|
|
- <code>doc_metadata</code> Document metadata (required if doc_type is provided)
|
Fields vary by doc_type:
|
|
For <code>book</code>:
|
- <code>title</code> Book title
|
Title of the book
|
- <code>language</code> Book language
|
Language of the book
|
- <code>author</code> Book author
|
Author of the book
|
- <code>publisher</code> Publisher name
|
Name of the publishing house
|
- <code>publication_date</code> Publication date
|
Date when the book was published
|
- <code>isbn</code> ISBN number
|
International Standard Book Number
|
- <code>category</code> Book category
|
Category or genre of the book
|
|
For <code>web_page</code>:
|
- <code>title</code> Page title
|
Title of the web page
|
- <code>url</code> Page URL
|
URL address of the web page
|
- <code>language</code> Page language
|
Language of the web page
|
- <code>publish_date</code> Publish date
|
Date when the web page was published
|
- <code>author/publisher</code> Author or publisher
|
Author or publisher of the web page
|
- <code>topic/keywords</code> Topic or keywords
|
Topics or keywords of the web page
|
- <code>description</code> Page description
|
Description of the web page content
|
|
Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
|
For doc_type "others", any valid JSON object is accepted
|
|
- <code>doc_language</code> In Q&A mode, specify the language of the document, for example: <code>English</code>, <code>Chinese</code>
|
|
- <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
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
- enumerate
|
- <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
|
- <code>parent_mode</code> Retrieval mode of parent chunks: <code>full-doc</code> full text retrieval / <code>paragraph</code> paragraph retrieval
|
- <code>subchunk_segmentation</code> (object) Child chunk rules
|
- <code>separator</code> Segmentation identifier. Currently, only one delimiter is allowed. The default is <code>***</code>
|
- <code>max_tokens</code> The maximum length (tokens) must be validated to be shorter than the length of the parent chunk
|
- <code>chunk_overlap</code> Define the overlap between adjacent chunks (optional)
|
</Property>
|
<Property name='file' type='multipart/form-data' key='file'>
|
Files that need to be uploaded.
|
</Property>
|
<PropertyInstruction>When no parameters are set for the knowledge base, the first upload requires the following parameters to be provided; if not provided, the default parameters will be used.</PropertyInstruction>
|
<Property name='retrieval_model' type='object' key='retrieval_model'>
|
Retrieval model
|
- <code>search_method</code> (string) Search method
|
- <code>hybrid_search</code> Hybrid search
|
- <code>semantic_search</code> Semantic search
|
- <code>full_text_search</code> Full-text search
|
- <code>reranking_enable</code> (bool) Whether to enable reranking
|
- <code>reranking_mode</code> (object) Rerank model configuration
|
- <code>reranking_provider_name</code> (string) Rerank model provider
|
- <code>reranking_model_name</code> (string) Rerank model name
|
- <code>top_k</code> (int) Number of results to return
|
- <code>score_threshold_enabled</code> (bool) Whether to enable score threshold
|
- <code>score_threshold</code> (float) Score threshold
|
</Property>
|
<Property name='embedding_model' type='string' key='embedding_model'>
|
Embedding model name
|
</Property>
|
<Property name='embedding_model_provider' type='string' key='embedding_model_provider'>
|
Embedding model provider
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/document/create-by-file"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/document/create-by-file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${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"'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"document": {
|
"id": "",
|
"position": 1,
|
"data_source_type": "upload_file",
|
"data_source_info": {
|
"upload_file_id": ""
|
},
|
"dataset_process_rule_id": "",
|
"name": "Dify.txt",
|
"created_from": "api",
|
"created_by": "",
|
"created_at": 1695308667,
|
"tokens": 0,
|
"indexing_status": "waiting",
|
"error": null,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"archived": false,
|
"display_status": "queuing",
|
"word_count": 0,
|
"hit_count": 0,
|
"doc_form": "text_model"
|
},
|
"batch": ""
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets'
|
method='POST'
|
title='Create an Empty Knowledge Base'
|
name='#create_empty_dataset'
|
/>
|
<Row>
|
<Col>
|
### Request Body
|
<Properties>
|
<Property name='name' type='string' key='name'>
|
Knowledge name
|
</Property>
|
<Property name='description' type='string' key='description'>
|
Knowledge description (optional)
|
</Property>
|
<Property name='doc_type' type='string' key='doc_type'>
|
Type of document (optional):
|
- <code>book</code> Book
|
- <code>web_page</code> Web page
|
- <code>paper</code> Academic paper/article
|
- <code>social_media_post</code> Social media post
|
- <code>wikipedia_entry</code> Wikipedia entry
|
- <code>personal_document</code> Personal document
|
- <code>business_document</code> Business document
|
- <code>im_chat_log</code> Chat log
|
- <code>synced_from_notion</code> Notion document
|
- <code>synced_from_github</code> GitHub document
|
- <code>others</code> Other document types
|
</Property>
|
<Property name='doc_metadata' type='object' key='doc_metadata'>
|
Document metadata (required if doc_type is provided). Fields vary by doc_type:
|
For <code>book</code>:
|
- <code>title</code> Book title
|
- <code>language</code> Book language
|
- <code>author</code> Book author
|
- <code>publisher</code> Publisher name
|
- <code>publication_date</code> Publication date
|
- <code>isbn</code> ISBN number
|
- <code>category</code> Book category
|
|
For <code>web_page</code>:
|
- <code>title</code> Page title
|
- <code>url</code> Page URL
|
- <code>language</code> Page language
|
- <code>publish_date</code> Publish date
|
- <code>author/publisher</code> Author or publisher
|
- <code>topic/keywords</code> Topic or keywords
|
- <code>description</code> Page description
|
|
Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
|
|
For doc_type "others", any valid JSON object is accepted
|
</Property>
|
<Property name='indexing_technique' type='string' key='indexing_technique'>
|
Index technique (optional)
|
- <code>high_quality</code> High quality
|
- <code>economy</code> Economy
|
</Property>
|
<Property name='permission' type='string' key='permission'>
|
Permission
|
- <code>only_me</code> Only me
|
- <code>all_team_members</code> All team members
|
- <code>partial_members</code> Partial members
|
</Property>
|
<Property name='provider' type='string' key='provider'>
|
Provider (optional, default: vendor)
|
- <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)
|
</Property>
|
<Property name='external_knowledge_id' type='str' key='external_knowledge_id'>
|
External knowledge ID (optional)
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name", "permission": "only_me"}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${apiBaseUrl}/v1/datasets' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json' \
|
--data-raw '{
|
"name": "name",
|
"permission": "only_me"
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"id": "",
|
"name": "name",
|
"description": null,
|
"provider": "vendor",
|
"permission": "only_me",
|
"data_source_type": null,
|
"indexing_technique": null,
|
"app_count": 0,
|
"document_count": 0,
|
"word_count": 0,
|
"created_by": "",
|
"created_at": 1695636173,
|
"updated_by": "",
|
"updated_at": 1695636173,
|
"embedding_model": null,
|
"embedding_model_provider": null,
|
"embedding_available": null
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets'
|
method='GET'
|
title='Get Knowledge Base List'
|
name='#dataset_list'
|
/>
|
<Row>
|
<Col>
|
### Query
|
<Properties>
|
<Property name='page' type='string' key='page'>
|
Page number
|
</Property>
|
<Property name='limit' type='string' key='limit'>
|
Number of items returned, default 20, range 1-100
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="GET"
|
label="/datasets"
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request GET '${props.apiBaseUrl}/datasets?page=1&limit=20' \
|
--header 'Authorization: Bearer {api_key}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data": [
|
{
|
"id": "",
|
"name": "name",
|
"description": "desc",
|
"permission": "only_me",
|
"data_source_type": "upload_file",
|
"indexing_technique": "",
|
"app_count": 2,
|
"document_count": 10,
|
"word_count": 1200,
|
"created_by": "",
|
"created_at": "",
|
"updated_by": "",
|
"updated_at": ""
|
},
|
...
|
],
|
"has_more": true,
|
"limit": 20,
|
"total": 50,
|
"page": 1
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}'
|
method='DELETE'
|
title='Delete a Knowledge Base'
|
name='#delete_dataset'
|
/>
|
<Row>
|
<Col>
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="DELETE"
|
label="/datasets/{dataset_id}"
|
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}' \
|
--header 'Authorization: Bearer {api_key}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```text {{ title: 'Response' }}
|
204 No Content
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/update-by-text'
|
method='POST'
|
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.
|
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
|
### Request Body
|
<Properties>
|
<Property name='name' type='string' key='name'>
|
Document name (optional)
|
</Property>
|
<Property name='text' type='string' key='text'>
|
Document content (optional)
|
</Property>
|
<Property name='process_rule' type='object' key='process_rule'>
|
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
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
- enumerate
|
- <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
|
- <code>parent_mode</code> Retrieval mode of parent chunks: <code>full-doc</code> full text retrieval / <code>paragraph</code> paragraph retrieval
|
- <code>subchunk_segmentation</code> (object) Child chunk rules
|
- <code>separator</code> Segmentation identifier. Currently, only one delimiter is allowed. The default is <code>***</code>
|
- <code>max_tokens</code> The maximum length (tokens) must be validated to be shorter than the length of the parent chunk
|
- <code>chunk_overlap</code> Define the overlap between adjacent chunks (optional)
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/documents/{document_id}/update-by-text"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-text' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"name": "name","text": "text"}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-text' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json' \
|
--data-raw '{
|
"name": "name",
|
"text": "text"
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"document": {
|
"id": "",
|
"position": 1,
|
"data_source_type": "upload_file",
|
"data_source_info": {
|
"upload_file_id": ""
|
},
|
"dataset_process_rule_id": "",
|
"name": "name.txt",
|
"created_from": "api",
|
"created_by": "",
|
"created_at": 1695308667,
|
"tokens": 0,
|
"indexing_status": "waiting",
|
"error": null,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"archived": false,
|
"display_status": "queuing",
|
"word_count": 0,
|
"hit_count": 0,
|
"doc_form": "text_model"
|
},
|
"batch": ""
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/update-by-file'
|
method='POST'
|
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
|
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
|
### Request Body
|
<Properties>
|
<Property name='name' type='string' key='name'>
|
Document name (optional)
|
</Property>
|
<Property name='file' type='multipart/form-data' key='file'>
|
Files to be uploaded
|
</Property>
|
<Property name='process_rule' type='object' key='process_rule'>
|
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
|
- <code>id</code> (string) Unique identifier for the preprocessing rule
|
- enumerate
|
- <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
|
- <code>parent_mode</code> Retrieval mode of parent chunks: <code>full-doc</code> full text retrieval / <code>paragraph</code> paragraph retrieval
|
- <code>subchunk_segmentation</code> (object) Child chunk rules
|
- <code>separator</code> Segmentation identifier. Currently, only one delimiter is allowed. The default is <code>***</code>
|
- <code>max_tokens</code> The maximum length (tokens) must be validated to be shorter than the length of the parent chunk
|
- <code>chunk_overlap</code> Define the overlap between adjacent chunks (optional)
|
- <code>doc_type</code> Type of document (optional)
|
- <code>book</code> Book
|
Document records a book or publication
|
- <code>web_page</code> Web page
|
Document records web page content
|
- <code>paper</code> Academic paper/article
|
Document records academic paper or research article
|
- <code>social_media_post</code> Social media post
|
Content from social media posts
|
- <code>wikipedia_entry</code> Wikipedia entry
|
Content from Wikipedia entries
|
- <code>personal_document</code> Personal document
|
Documents related to personal content
|
- <code>business_document</code> Business document
|
Documents related to business content
|
- <code>im_chat_log</code> Chat log
|
Records of instant messaging chats
|
- <code>synced_from_notion</code> Notion document
|
Documents synchronized from Notion
|
- <code>synced_from_github</code> GitHub document
|
Documents synchronized from GitHub
|
- <code>others</code> Other document types
|
Other document types not listed above
|
|
- <code>doc_metadata</code> Document metadata (required if doc_type is provided)
|
Fields vary by doc_type:
|
|
For <code>book</code>:
|
- <code>title</code> Book title
|
Title of the book
|
- <code>language</code> Book language
|
Language of the book
|
- <code>author</code> Book author
|
Author of the book
|
- <code>publisher</code> Publisher name
|
Name of the publishing house
|
- <code>publication_date</code> Publication date
|
Date when the book was published
|
- <code>isbn</code> ISBN number
|
International Standard Book Number
|
- <code>category</code> Book category
|
Category or genre of the book
|
|
For <code>web_page</code>:
|
- <code>title</code> Page title
|
Title of the web page
|
- <code>url</code> Page URL
|
URL address of the web page
|
- <code>language</code> Page language
|
Language of the web page
|
- <code>publish_date</code> Publish date
|
Date when the web page was published
|
- <code>author/publisher</code> Author or publisher
|
Author or publisher of the web page
|
- <code>topic/keywords</code> Topic or keywords
|
Topics or keywords of the web page
|
- <code>description</code> Page description
|
Description of the web page content
|
|
Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
|
For doc_type "others", any valid JSON object is accepted
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/documents/{document_id}/update-by-file"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/update-by-file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--form 'data="{"name":"Dify","indexing_technique":"high_quality","process_rule":{"rules":{"pre_processing_rules":[{"id":"remove_extra_spaces","enabled":true},{"id":"remove_urls_emails","enabled":true}],"segmentation":{"separator":"###","max_tokens":500}},"mode":"custom"}}";type=text/plain' \\\n--form 'file=@"/path/to/file"'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${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"'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"document": {
|
"id": "",
|
"position": 1,
|
"data_source_type": "upload_file",
|
"data_source_info": {
|
"upload_file_id": ""
|
},
|
"dataset_process_rule_id": "",
|
"name": "Dify.txt",
|
"created_from": "api",
|
"created_by": "",
|
"created_at": 1695308667,
|
"tokens": 0,
|
"indexing_status": "waiting",
|
"error": null,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"archived": false,
|
"display_status": "queuing",
|
"word_count": 0,
|
"hit_count": 0,
|
"doc_form": "text_model"
|
},
|
"batch": "20230921150427533684"
|
}
|
```
|
</CodeGroup>
|
</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)'
|
name='#indexing_status'
|
/>
|
<Row>
|
<Col>
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='batch' type='string' key='batch'>
|
Batch number of uploaded documents
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="GET"
|
label="/datasets/{dataset_id}/documents/{batch}/indexing-status"
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \\\n--header 'Authorization: Bearer {api_key}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \
|
--header 'Authorization: Bearer {api_key}' \
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data":[{
|
"id": "",
|
"indexing_status": "indexing",
|
"processing_started_at": 1681623462.0,
|
"parsing_completed_at": 1681623462.0,
|
"cleaning_completed_at": 1681623462.0,
|
"splitting_completed_at": 1681623462.0,
|
"completed_at": null,
|
"paused_at": null,
|
"error": null,
|
"stopped_at": null,
|
"completed_segments": 24,
|
"total_segments": 100
|
}]
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}'
|
method='DELETE'
|
title='Delete a Document'
|
name='#delete_document'
|
/>
|
<Row>
|
<Col>
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="DELETE"
|
label="/datasets/{dataset_id}/documents/{document_id}"
|
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
|
--header 'Authorization: Bearer {api_key}' \
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"result": "success"
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents'
|
method='GET'
|
title='Get the Document List of a Knowledge Base'
|
name='#dataset_document_list'
|
/>
|
<Row>
|
<Col>
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
</Properties>
|
|
### Query
|
<Properties>
|
<Property name='keyword' type='string' key='keyword'>
|
Search keywords, currently only search document names (optional)
|
</Property>
|
<Property name='page' type='string' key='page'>
|
Page number (optional)
|
</Property>
|
<Property name='limit' type='string' key='limit'>
|
Number of items returned, default 20, range 1-100 (optional)
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="GET"
|
label="/datasets/{dataset_id}/documents"
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \\\n--header 'Authorization: Bearer {api_key}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \
|
--header 'Authorization: Bearer {api_key}' \
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data": [
|
{
|
"id": "",
|
"position": 1,
|
"data_source_type": "file_upload",
|
"data_source_info": null,
|
"dataset_process_rule_id": null,
|
"name": "dify",
|
"created_from": "",
|
"created_by": "",
|
"created_at": 1681623639,
|
"tokens": 0,
|
"indexing_status": "waiting",
|
"error": null,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"archived": false
|
},
|
],
|
"has_more": false,
|
"limit": 20,
|
"total": 9,
|
"page": 1
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
method='POST'
|
title='Add Chunks to a Document'
|
name='#create_new_segment'
|
/>
|
<Row>
|
<Col>
|
### Params
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
|
### 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 Q&A mode, pass the value (optional)
|
- <code>keywords</code> (list) Keywords (optional)
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/documents/{document_id}/segments"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"segments": [{"content": "1","answer": "1","keywords": ["a"]}]}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json' \
|
--data-raw '{
|
"segments": [
|
{
|
"content": "1",
|
"answer": "1",
|
"keywords": ["a"]
|
}
|
]
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data": [{
|
"id": "",
|
"position": 1,
|
"document_id": "",
|
"content": "1",
|
"answer": "1",
|
"word_count": 25,
|
"tokens": 0,
|
"keywords": [
|
"a"
|
],
|
"index_node_id": "",
|
"index_node_hash": "",
|
"hit_count": 0,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"status": "completed",
|
"created_by": "",
|
"created_at": 1695312007,
|
"indexing_at": 1695312007,
|
"completed_at": 1695312007,
|
"error": null,
|
"stopped_at": null
|
}],
|
"doc_form": "text_model"
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
method='GET'
|
title='Get Chunks from a Document'
|
name='#get_segment'
|
/>
|
<Row>
|
<Col>
|
### Path
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
|
### Query
|
<Properties>
|
<Property name='keyword' type='string' key='keyword'>
|
Keyword (optional)
|
</Property>
|
<Property name='status' type='string' key='status'>
|
Search status, completed
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="GET"
|
label="/datasets/{dataset_id}/documents/{document_id}/segments"
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data": [{
|
"id": "",
|
"position": 1,
|
"document_id": "",
|
"content": "1",
|
"answer": "1",
|
"word_count": 25,
|
"tokens": 0,
|
"keywords": [
|
"a"
|
],
|
"index_node_id": "",
|
"index_node_hash": "",
|
"hit_count": 0,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"status": "completed",
|
"created_by": "",
|
"created_at": 1695312007,
|
"indexing_at": 1695312007,
|
"completed_at": 1695312007,
|
"error": null,
|
"stopped_at": null
|
}],
|
"doc_form": "text_model"
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
|
method='DELETE'
|
title='Delete a Chunk in a Document'
|
name='#delete_segment'
|
/>
|
<Row>
|
<Col>
|
### Path
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
<Property name='segment_id' type='string' key='segment_id'>
|
Document Segment ID
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="DELETE"
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
|
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"result": "success"
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
|
method='POST'
|
title='Update a Chunk in a Document'
|
name='#update_segment'
|
/>
|
<Row>
|
<Col>
|
### POST
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
<Property name='segment_id' type='string' key='segment_id'>
|
Document Segment ID
|
</Property>
|
</Properties>
|
|
### 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, passed if the knowledge is in Q&A mode (optional)
|
- <code>keywords</code> (list) Keyword (optional)
|
- <code>enabled</code> (bool) False / true (optional)
|
- <code>regenerate_child_chunks</code> (bool) Whether to regenerate child chunks (optional)
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'\\\n--data-raw '{\"segment\": {\"content\": \"1\",\"answer\": \"1\", \"keywords\": [\"a\"], \"enabled\": false}}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
|
--header 'Content-Type: application/json' \
|
--data-raw '{
|
"segment": {
|
"content": "1",
|
"answer": "1",
|
"keywords": ["a"],
|
"enabled": false
|
}
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"data": [{
|
"id": "",
|
"position": 1,
|
"document_id": "",
|
"content": "1",
|
"answer": "1",
|
"word_count": 25,
|
"tokens": 0,
|
"keywords": [
|
"a"
|
],
|
"index_node_id": "",
|
"index_node_hash": "",
|
"hit_count": 0,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"status": "completed",
|
"created_by": "",
|
"created_at": 1695312007,
|
"indexing_at": 1695312007,
|
"completed_at": 1695312007,
|
"error": null,
|
"stopped_at": null
|
}],
|
"doc_form": "text_model"
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/documents/{document_id}/upload-file'
|
method='GET'
|
title='Get Upload File'
|
name='#get_upload_file'
|
/>
|
<Row>
|
<Col>
|
### Path
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
<Property name='document_id' type='string' key='document_id'>
|
Document ID
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="GET"
|
label="/datasets/{dataset_id}/documents/{document_id}/upload-file"
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/upload-file' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/upload-file' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"id": "file_id",
|
"name": "file_name",
|
"size": 1024,
|
"extension": "txt",
|
"url": "preview_url",
|
"download_url": "download_url",
|
"mime_type": "text/plain",
|
"created_by": "user_id",
|
"created_at": 1728734540,
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<Heading
|
url='/datasets/{dataset_id}/retrieve'
|
method='POST'
|
title='Retrieve Chunks from a Knowledge Base'
|
name='#dataset_retrieval'
|
/>
|
<Row>
|
<Col>
|
### Path
|
<Properties>
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
Knowledge ID
|
</Property>
|
</Properties>
|
|
### Request Body
|
<Properties>
|
<Property name='query' type='string' key='query'>
|
Query keyword
|
</Property>
|
<Property name='retrieval_model' type='object' key='retrieval_model'>
|
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, 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> (float) Semantic search weight setting in hybrid search mode
|
- <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> (float) Score threshold
|
</Property>
|
<Property name='external_retrieval_model' type='object' key='external_retrieval_model'>
|
Unused field
|
</Property>
|
</Properties>
|
</Col>
|
<Col sticky>
|
<CodeGroup
|
title="Request"
|
tag="POST"
|
label="/datasets/{dataset_id}/retrieve"
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/retrieve' \\\n--header 'Authorization: Bearer {api_key}'\\\n--header 'Content-Type: application/json'\\\n--data-raw '{
|
"query": "test",
|
"retrieval_model": {
|
"search_method": "keyword_search",
|
"reranking_enable": false,
|
"reranking_mode": null,
|
"reranking_model": {
|
"reranking_provider_name": "",
|
"reranking_model_name": ""
|
},
|
"weights": null,
|
"top_k": 1,
|
"score_threshold_enabled": false,
|
"score_threshold": null
|
}
|
}'`}
|
>
|
```bash {{ title: 'cURL' }}
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/retrieve' \
|
--header 'Authorization: Bearer {api_key}' \
|
--header 'Content-Type: application/json' \
|
--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": 2,
|
"score_threshold_enabled": false,
|
"score_threshold": null
|
}
|
}'
|
```
|
</CodeGroup>
|
<CodeGroup title="Response">
|
```json {{ title: 'Response' }}
|
{
|
"query": {
|
"content": "test"
|
},
|
"records": [
|
{
|
"segment": {
|
"id": "7fa6f24f-8679-48b3-bc9d-bdf28d73f218",
|
"position": 1,
|
"document_id": "a8c6c36f-9f5d-4d7a-8472-f5d7b75d71d2",
|
"content": "Operation guide",
|
"answer": null,
|
"word_count": 847,
|
"tokens": 280,
|
"keywords": [
|
"install",
|
"java",
|
"base",
|
"scripts",
|
"jdk",
|
"manual",
|
"internal",
|
"opens",
|
"add",
|
"vmoptions"
|
],
|
"index_node_id": "39dd8443-d960-45a8-bb46-7275ad7fbc8e",
|
"index_node_hash": "0189157697b3c6a418ccf8264a09699f25858975578f3467c76d6bfc94df1d73",
|
"hit_count": 0,
|
"enabled": true,
|
"disabled_at": null,
|
"disabled_by": null,
|
"status": "completed",
|
"created_by": "dbcb1ab5-90c8-41a7-8b78-73b235eb6f6f",
|
"created_at": 1728734540,
|
"indexing_at": 1728734552,
|
"completed_at": 1728734584,
|
"error": null,
|
"stopped_at": null,
|
"document": {
|
"id": "a8c6c36f-9f5d-4d7a-8472-f5d7b75d71d2",
|
"data_source_type": "upload_file",
|
"name": "readme.txt",
|
"doc_type": null
|
}
|
},
|
"score": 3.730463140527718e-05,
|
"tsne_position": null
|
}
|
]
|
}
|
```
|
</CodeGroup>
|
</Col>
|
</Row>
|
|
<hr className='ml-0 mr-0' />
|
|
<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 className="p-2 border border-slate-300">code</th>
|
<th className="p-2 border border-slate-300">status</th>
|
<th className="p-2 border border-slate-300">message</th>
|
</tr>
|
</thead>
|
<tbody>
|
<tr>
|
<td className="p-2 border border-slate-300">no_file_uploaded</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">Please upload your file.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">too_many_files</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">Only one file is allowed.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">file_too_large</td>
|
<td className="p-2 border border-slate-300">413</td>
|
<td className="p-2 border border-slate-300">File size exceeded.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">unsupported_file_type</td>
|
<td className="p-2 border border-slate-300">415</td>
|
<td className="p-2 border border-slate-300">File type not allowed.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">high_quality_dataset_only</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">Current operation only supports 'high-quality' datasets.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">dataset_not_initialized</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">The dataset is still being initialized or indexing. Please wait a moment.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">archived_document_immutable</td>
|
<td className="p-2 border border-slate-300">403</td>
|
<td className="p-2 border border-slate-300">The archived document is not editable.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">dataset_name_duplicate</td>
|
<td className="p-2 border border-slate-300">409</td>
|
<td className="p-2 border border-slate-300">The dataset name already exists. Please modify your dataset name.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">invalid_action</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">Invalid action.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">document_already_finished</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="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 className="p-2 border border-slate-300">document_indexing</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">The document is being processed and cannot be edited.</td>
|
</tr>
|
<tr>
|
<td className="p-2 border border-slate-300">invalid_metadata</td>
|
<td className="p-2 border border-slate-300">400</td>
|
<td className="p-2 border border-slate-300">The metadata content is incorrect. Please check and verify.</td>
|
</tr>
|
</tbody>
|
</table>
|
<div className="pb-4" />
|
