|
@@ -0,0 +1,1319 @@
|
|
|
+import { CodeGroup } from '@/app/components/develop/code.tsx'
|
|
|
+import { Row, Col, Properties, Property, Heading, SubProperty, 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<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='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='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
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/document/create_by_file'
|
|
|
+ method='POST'
|
|
|
+ title='Create documents from files'
|
|
|
+ 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'>
|
|
|
+ - original_document_id 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>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
|
|
|
+
|
|
|
+ - 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
|
|
|
+ </Property>
|
|
|
+ <Property name='file' type='multipart/form-data' key='file'>
|
|
|
+ Files that need to be uploaded.
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets'
|
|
|
+ method='POST'
|
|
|
+ title='Create an empty Knowledge'
|
|
|
+ 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='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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets'
|
|
|
+ method='GET'
|
|
|
+ title='Knowledge 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="POST"
|
|
|
+ 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}'
|
|
|
+ method='DELETE'
|
|
|
+ title='Delete knowledge'
|
|
|
+ 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/update_by_text'
|
|
|
+ method='POST'
|
|
|
+ title='Update document via 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
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/update_by_file'
|
|
|
+ method='POST'
|
|
|
+ title='Update a document from 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
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}'
|
|
|
+ method='DELETE'
|
|
|
+ title='Delete 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents'
|
|
|
+ method='GET'
|
|
|
+ title='Knowledge document list'
|
|
|
+ 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
|
|
+ method='POST'
|
|
|
+ title='Add segment'
|
|
|
+ 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 qa 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
|
|
+ method='GET'
|
|
|
+ title='get documents segments'
|
|
|
+ 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,choosable
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
|
|
|
+ method='DELETE'
|
|
|
+ title='delete document segment'
|
|
|
+ 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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}'
|
|
|
+ method='POST'
|
|
|
+ title='update document segment'
|
|
|
+ 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, 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
|
|
|
+ </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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<Heading
|
|
|
+ url='/datasets/{dataset_id}/hit_testing'
|
|
|
+ method='POST'
|
|
|
+ title='Dataset hit testing'
|
|
|
+ name='#dataset_hit_testing'
|
|
|
+/>
|
|
|
+<Row>
|
|
|
+ <Col>
|
|
|
+ ### Path
|
|
|
+ <Properties>
|
|
|
+ <Property name='dataset_id' type='string' key='dataset_id'>
|
|
|
+ Dataset ID
|
|
|
+ </Property>
|
|
|
+ </Properties>
|
|
|
+
|
|
|
+ ### Request Body
|
|
|
+ <Properties>
|
|
|
+ <Property name='query' type='string' key='query'>
|
|
|
+ retrieval keywordc
|
|
|
+ </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)
|
|
|
+ - <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_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>score_threshold_enabled</code> (bool) Whether to enable score threshold
|
|
|
+ - <code>score_threshold</code> (double) 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}/hit_testing"
|
|
|
+ targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/hit_testing' \\\n--header 'Authorization: Bearer {api_key}'\\\n--header 'Content-Type: application/json'\\\n--data-raw '{
|
|
|
+ "query": "test",
|
|
|
+ "retrieval_model": {
|
|
|
+ "search_method": "keyword_search",
|
|
|
+ "reranking_enable": false,
|
|
|
+ "reranking_mode": null,
|
|
|
+ "reranking_model": {
|
|
|
+ "reranking_provider_name": "",
|
|
|
+ "reranking_model_name": ""
|
|
|
+ },
|
|
|
+ "weights": null,
|
|
|
+ "top_k": 1,
|
|
|
+ "score_threshold_enabled": false,
|
|
|
+ "score_threshold": null
|
|
|
+ }
|
|
|
+ }'`}
|
|
|
+ >
|
|
|
+ ```bash {{ title: 'cURL' }}
|
|
|
+ curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/hit_testing' \
|
|
|
+ --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>
|
|
|
+
|
|
|
+---
|
|
|
+
|
|
|
+<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" />
|