From a430284aa21e3ae1f0d5654e55b2ad2852519cc2 Mon Sep 17 00:00:00 2001
From: wwf <yearningwang@iqtogether.com>
Date: 星期三, 04 六月 2025 15:17:49 +0800
Subject: [PATCH] 初始化
---
app/(commonLayout)/datasets/template/template.en.mdx | 1152 +++++++++++----------------------------------------------
1 files changed, 224 insertions(+), 928 deletions(-)
diff --git "a/app/\050commonLayout\051/datasets/template/template.en.mdx" "b/app/\050commonLayout\051/datasets/template/template.en.mdx"
index 7f28610..ac57e3a 100644
--- "a/app/\050commonLayout\051/datasets/template/template.en.mdx"
+++ "b/app/\050commonLayout\051/datasets/template/template.en.mdx"
@@ -1,8 +1,3 @@
-{/**
- * @typedef Props
- * @property {string} apiBaseUrl
- */}
-
import { CodeGroup } from '@/app/components/develop/code.tsx'
import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstruction, Paragraph } from '@/app/components/develop/md.tsx'
@@ -37,7 +32,7 @@
<Col>
This API is based on an existing knowledge and creates a new document through text based on this knowledge.
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -51,6 +46,44 @@
</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
@@ -175,7 +208,7 @@
<Col>
This API is based on an existing knowledge and creates a new document through a file based on this knowledge.
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -199,6 +232,68 @@
- <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>
@@ -312,9 +407,46 @@
<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)
- If this is not set, embedding_model, embedding_model_provider and retrieval_model will be set to null
- <code>high_quality</code> High quality
- <code>economy</code> Economy
</Property>
@@ -334,26 +466,6 @@
</Property>
<Property name='external_knowledge_id' type='str' key='external_knowledge_id'>
External knowledge ID (optional)
- </Property>
- <Property name='embedding_model' type='str' key='embedding_model'>
- Embedding model name (optional)
- </Property>
- <Property name='embedding_model_provider' type='str' key='embedding_model_provider'>
- Embedding model provider name (optional)
- </Property>
- <Property name='retrieval_model' type='object' key='retrieval_model'>
- Retrieval model (optional)
- - <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_model</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>
</Properties>
</Col>
@@ -412,20 +524,11 @@
<Col>
### Query
<Properties>
- <Property name='keyword' type='string' key='keyword'>
- Search keyword, optional
- </Property>
- <Property name='tag_ids' type='array[string]' key='tag_ids'>
- Tag ID list, optional
- </Property>
<Property name='page' type='string' key='page'>
- Page number, optional, default 1
+ Page number
</Property>
<Property name='limit' type='string' key='limit'>
- Number of items returned, optional, default 20, range 1-100
- </Property>
- <Property name='include_all' type='boolean' key='include_all'>
- Whether to include all datasets (only effective for owners), optional, defaults to false
+ Number of items returned, default 20, range 1-100
</Property>
</Properties>
</Col>
@@ -476,255 +579,13 @@
<Heading
url='/datasets/{dataset_id}'
- method='GET'
- title='Get knowledge base details by knowledge base ID'
- name='#view_dataset'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge Base ID
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="GET"
- label="/datasets/{dataset_id}"
- targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}' \
- --header 'Authorization: Bearer {api_key}'
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "id": "eaedb485-95ac-4ffd-ab1e-18da6d676a2f",
- "name": "Test Knowledge Base",
- "description": "",
- "provider": "vendor",
- "permission": "only_me",
- "data_source_type": null,
- "indexing_technique": null,
- "app_count": 0,
- "document_count": 0,
- "word_count": 0,
- "created_by": "e99a1635-f725-4951-a99a-1daaaa76cfc6",
- "created_at": 1735620612,
- "updated_by": "e99a1635-f725-4951-a99a-1daaaa76cfc6",
- "updated_at": 1735620612,
- "embedding_model": null,
- "embedding_model_provider": null,
- "embedding_available": true,
- "retrieval_model_dict": {
- "search_method": "semantic_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
- },
- "tags": [],
- "doc_form": null,
- "external_knowledge_info": {
- "external_knowledge_id": null,
- "external_knowledge_api_id": null,
- "external_knowledge_api_name": null,
- "external_knowledge_api_endpoint": null
- },
- "external_retrieval_model": {
- "top_k": 2,
- "score_threshold": 0.0,
- "score_threshold_enabled": null
- }
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}'
- method='PATCH'
- title='Update knowledge base'
- name='#update_dataset'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge Base ID
- </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='embedding_model_provider' type='string' key='embedding_model_provider'>
- Specified embedding model provider, must be set up in the system first, corresponding to the provider field(Optional)
- </Property>
- <Property name='embedding_model' type='string' key='embedding_model'>
- Specified embedding model, corresponding to the model field(Optional)
- </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='partial_member_list' type='array' key='partial_member_list'>
- Partial member list(Optional)
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="PATCH"
- label="/datasets/{dataset_id}"
- targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{
- "name": "Test Knowledge Base",
- "indexing_technique": "high_quality",
- "permission": "only_me",
- "embedding_model_provider": "zhipuai",
- "embedding_model": "embedding-3",
- "retrieval_model": {
- "search_method": "keyword_search",
- "reranking_enable": false,
- "reranking_mode": null,
- "reranking_model": {
- "reranking_provider_name": "",
- "reranking_model_name": ""
- },
- "weights": null,
- "top_k": 1,
- "score_threshold_enabled": false,
- "score_threshold": null
- },
- "partial_member_list": []
- }'
- `}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}' \
- --header 'Authorization: Bearer {api_key}' \
- --header 'Content-Type: application/json' \
- --data-raw '{
- "name": "Test Knowledge Base",
- "indexing_technique": "high_quality",
- "permission": "only_me",
- "embedding_model_provider": "zhipuai",
- "embedding_model": "embedding-3",
- "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
- },
- "partial_member_list": []
- }'
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "id": "eaedb485-95ac-4ffd-ab1e-18da6d676a2f",
- "name": "Test Knowledge Base",
- "description": "",
- "provider": "vendor",
- "permission": "only_me",
- "data_source_type": null,
- "indexing_technique": "high_quality",
- "app_count": 0,
- "document_count": 0,
- "word_count": 0,
- "created_by": "e99a1635-f725-4951-a99a-1daaaa76cfc6",
- "created_at": 1735620612,
- "updated_by": "e99a1635-f725-4951-a99a-1daaaa76cfc6",
- "updated_at": 1735622679,
- "embedding_model": "embedding-3",
- "embedding_model_provider": "zhipuai",
- "embedding_available": null,
- "retrieval_model_dict": {
- "search_method": "semantic_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
- },
- "tags": [],
- "doc_form": null,
- "external_knowledge_info": {
- "external_knowledge_id": null,
- "external_knowledge_api_id": null,
- "external_knowledge_api_name": null,
- "external_knowledge_api_endpoint": null
- },
- "external_retrieval_model": {
- "top_k": 2,
- "score_threshold": 0.0,
- "score_threshold_enabled": null
- },
- "partial_member_list": []
- }
- ```
- </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>
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -763,7 +624,7 @@
<Col>
This API is based on an existing knowledge and updates the document through text based on this knowledge.
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -865,7 +726,7 @@
<Col>
This API is based on an existing knowledge, and updates documents through files based on this knowledge
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -901,6 +762,67 @@
- <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>
@@ -962,7 +884,7 @@
/>
<Row>
<Col>
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -1017,7 +939,7 @@
/>
<Row>
<Col>
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -1040,8 +962,10 @@
```
</CodeGroup>
<CodeGroup title="Response">
- ```text {{ title: 'Response' }}
- 204 No Content
+ ```json {{ title: 'Response' }}
+ {
+ "result": "success"
+ }
```
</CodeGroup>
</Col>
@@ -1057,7 +981,7 @@
/>
<Row>
<Col>
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -1132,7 +1056,7 @@
/>
<Row>
<Col>
- ### Path
+ ### Params
<Properties>
<Property name='dataset_id' type='string' key='dataset_id'>
Knowledge ID
@@ -1236,12 +1160,6 @@
<Property name='status' type='string' key='status'>
Search status, completed
</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>
@@ -1285,11 +1203,7 @@
"error": null,
"stopped_at": null
}],
- "doc_form": "text_model",
- "has_more": false,
- "limit": 20,
- "total": 9,
- "page": 1
+ "doc_form": "text_model"
}
```
</CodeGroup>
@@ -1324,17 +1238,19 @@
title="Request"
tag="DELETE"
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}"
- targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'`}
+ targetCode={`curl --location --request DELETE '${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 '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}' \
+ curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}' \
--header 'Authorization: Bearer {api_key}' \
--header 'Content-Type: application/json'
```
</CodeGroup>
<CodeGroup title="Response">
- ```text {{ title: 'Response' }}
- 204 No Content
+ ```json {{ title: 'Response' }}
+ {
+ "result": "success"
+ }
```
</CodeGroup>
</Col>
@@ -1397,7 +1313,7 @@
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
- "data": {
+ "data": [{
"id": "",
"position": 1,
"document_id": "",
@@ -1421,276 +1337,8 @@
"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}/child_chunks'
- method='POST'
- title='Create Child Chunk'
- name='#create_child_chunk'
-/>
-<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'>
- Segment ID
- </Property>
- </Properties>
-
- ### Request Body
- <Properties>
- <Property name='content' type='string' key='content'>
- Child chunk content
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="POST"
- label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks"
- targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"content": "Child chunk content"}'`}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks' \
- --header 'Authorization: Bearer {api_key}' \
- --header 'Content-Type: application/json' \
- --data-raw '{
- "content": "Child chunk content"
- }'
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "data": {
- "id": "",
- "segment_id": "",
- "content": "Child chunk content",
- "word_count": 25,
- "tokens": 0,
- "index_node_id": "",
- "index_node_hash": "",
- "status": "completed",
- "created_by": "",
- "created_at": 1695312007,
- "indexing_at": 1695312007,
- "completed_at": 1695312007,
- "error": null,
- "stopped_at": null
- }
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks'
- method='GET'
- title='Get Child Chunks'
- name='#get_child_chunks'
-/>
-<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'>
- Segment ID
- </Property>
- </Properties>
-
- ### Query
- <Properties>
- <Property name='keyword' type='string' key='keyword'>
- Search keyword (optional)
- </Property>
- <Property name='page' type='integer' key='page'>
- Page number (optional, default: 1)
- </Property>
- <Property name='limit' type='integer' key='limit'>
- Items per page (optional, default: 20, max: 100)
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="GET"
- label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks"
- targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks?page=1&limit=20' \
- --header 'Authorization: Bearer {api_key}'
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "data": [{
- "id": "",
- "segment_id": "",
- "content": "Child chunk content",
- "word_count": 25,
- "tokens": 0,
- "index_node_id": "",
- "index_node_hash": "",
- "status": "completed",
- "created_by": "",
- "created_at": 1695312007,
- "indexing_at": 1695312007,
- "completed_at": 1695312007,
- "error": null,
- "stopped_at": null
}],
- "total": 1,
- "total_pages": 1,
- "page": 1,
- "limit": 20
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}'
- method='DELETE'
- title='Delete Child Chunk'
- name='#delete_child_chunk'
-/>
-<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'>
- Segment ID
- </Property>
- <Property name='child_chunk_id' type='string' key='child_chunk_id'>
- Child Chunk ID
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="DELETE"
- label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}"
- targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/segments/{segment_id}/child_chunks/{child_chunk_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}/segments/{segment_id}/child_chunks/{child_chunk_id}'
- method='PATCH'
- title='Update Child Chunk'
- name='#update_child_chunk'
-/>
-<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'>
- Segment ID
- </Property>
- <Property name='child_chunk_id' type='string' key='child_chunk_id'>
- Child Chunk ID
- </Property>
- </Properties>
-
- ### Request Body
- <Properties>
- <Property name='content' type='string' key='content'>
- Child chunk content
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="PATCH"
- label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}"
- targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"content": "Updated child chunk content"}'`}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \
- --header 'Authorization: Bearer {api_key}' \
- --header 'Content-Type: application/json' \
- --data-raw '{
- "content": "Updated child chunk content"
- }'
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "data": {
- "id": "",
- "segment_id": "",
- "content": "Updated child chunk content",
- "word_count": 25,
- "tokens": 0,
- "index_node_id": "",
- "index_node_hash": "",
- "status": "completed",
- "created_by": "",
- "created_at": 1695312007,
- "indexing_at": 1695312007,
- "completed_at": 1695312007,
- "error": null,
- "stopped_at": null
- }
+ "doc_form": "text_model"
}
```
</CodeGroup>
@@ -1880,6 +1528,7 @@
"id": "a8c6c36f-9f5d-4d7a-8472-f5d7b75d71d2",
"data_source_type": "upload_file",
"name": "readme.txt",
+ "doc_type": null
}
},
"score": 3.730463140527718e-05,
@@ -1890,359 +1539,6 @@
```
</CodeGroup>
</Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/metadata'
- method='POST'
- title='Create a Knowledge Metadata'
- name='#create_metadata'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- </Properties>
-
- ### Request Body
- <Properties>
- <Property name='segment' type='object' key='segment'>
- - <code>type</code> (string) Metadata type, required
- - <code>name</code> (string) Metadata name, required
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="POST"
- label="/datasets/{dataset_id}/metadata"
- targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/metadata' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'\\\n--data-raw '{"type": "string", "name": "test"}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "id": "abc",
- "type": "string",
- "name": "test",
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/metadata/{metadata_id}'
- method='PATCH'
- title='Update a Knowledge Metadata'
- name='#update_metadata'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- <Property name='metadata_id' type='string' key='metadata_id'>
- Metadata ID
- </Property>
- </Properties>
-
- ### Request Body
- <Properties>
- <Property name='segment' type='object' key='segment'>
- - <code>name</code> (string) Metadata name, required
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="PATCH"
- label="/datasets/{dataset_id}/metadata/{metadata_id}"
- targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/metadata/{metadata_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'\\\n--data-raw '{"name": "test"}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "id": "abc",
- "type": "string",
- "name": "test",
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/metadata/{metadata_id}'
- method='DELETE'
- title='Delete a Knowledge Metadata'
- name='#delete_metadata'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- <Property name='metadata_id' type='string' key='metadata_id'>
- Metadata ID
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="DELETE"
- label="/datasets/{dataset_id}/metadata/{metadata_id}"
- targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/metadata/{metadata_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/metadata/built-in/{action}'
- method='POST'
- title='Disable Or Enable Built-in Metadata'
- name='#toggle_metadata'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- <Property name='action' type='string' key='action'>
- disable/enable
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="POST"
- label="/datasets/{dataset_id}/metadata/built-in/{action}"
- targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/metadata/built-in/{action}' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/documents/metadata'
- method='POST'
- title='Update Documents Metadata'
- name='#update_documents_metadata'
-/>
-<Row>
- <Col>
- ### Path
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- </Properties>
-
- ### Request Body
- <Properties>
- <Property name='operation_data' type='object list' key='segments'>
- - <code>document_id</code> (string) Document ID
- - <code>metadata_list</code> (list) Metadata list
- - <code>id</code> (string) Metadata ID
- - <code>value</code> (string) Metadata value
- - <code>name</code> (string) Metadata name
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="POST"
- label="/datasets/{dataset_id}/documents/metadata"
- targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/metadata' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json'\\\n--data-raw '{"operation_data": [{"document_id": "document_id", "metadata_list": [{"id": "id", "value": "value", "name": "name"}]}]}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/datasets/{dataset_id}/metadata'
- method='GET'
- title='Get Knowledge Metadata List'
- name='#dataset_metadata_list'
-/>
-<Row>
- <Col>
- ### Params
- <Properties>
- <Property name='dataset_id' type='string' key='dataset_id'>
- Knowledge ID
- </Property>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="GET"
- label="/datasets/{dataset_id}/metadata"
- targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/metadata' \\\n--header 'Authorization: Bearer {api_key}'`}
- >
- ```bash {{ title: 'cURL' }}
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "doc_metadata": [
- {
- "id": "",
- "name": "name",
- "type": "string",
- "use_count": 0,
- },
- ...
- ],
- "built_in_field_enabled": true
- }
- ```
- </CodeGroup>
- </Col>
-</Row>
-
-<hr className='ml-0 mr-0' />
-
-<Heading
- url='/workspaces/current/models/model-types/text-embedding'
- method='GET'
- title='Get available embedding models'
- name='#model_type_list'
-/>
-<Row>
- <Col>
- ### Query
- <Properties>
- </Properties>
- </Col>
- <Col sticky>
- <CodeGroup
- title="Request"
- tag="GET"
- label="/datasets/{dataset_id}"
- targetCode={`curl --location --location --request GET '${props.apiBaseUrl}/workspaces/current/models/model-types/text-embedding' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' `}
- >
- ```bash {{ title: 'cURL' }}
- curl --location --request GET '${props.apiBaseUrl}/workspaces/current/models/model-types/text-embedding' \
- --header 'Authorization: Bearer {api_key}' \
- --header 'Content-Type: application/json' \
- ```
- </CodeGroup>
- <CodeGroup title="Response">
- ```json {{ title: 'Response' }}
- {
- "data": [
- {
- "provider": "zhipuai",
- "label": {
- "zh_Hans": "鏅鸿氨 AI",
- "en_US": "ZHIPU AI"
- },
- "icon_small": {
- "zh_Hans": "http://127.0.0.1:5001/console/api/workspaces/current/model-providers/zhipuai/icon_small/zh_Hans",
- "en_US": "http://127.0.0.1:5001/console/api/workspaces/current/model-providers/zhipuai/icon_small/en_US"
- },
- "icon_large": {
- "zh_Hans": "http://127.0.0.1:5001/console/api/workspaces/current/model-providers/zhipuai/icon_large/zh_Hans",
- "en_US": "http://127.0.0.1:5001/console/api/workspaces/current/model-providers/zhipuai/icon_large/en_US"
- },
- "status": "active",
- "models": [
- {
- "model": "embedding-3",
- "label": {
- "zh_Hans": "embedding-3",
- "en_US": "embedding-3"
- },
- "model_type": "text-embedding",
- "features": null,
- "fetch_from": "predefined-model",
- "model_properties": {
- "context_size": 8192
- },
- "deprecated": false,
- "status": "active",
- "load_balancing_enabled": false
- },
- {
- "model": "embedding-2",
- "label": {
- "zh_Hans": "embedding-2",
- "en_US": "embedding-2"
- },
- "model_type": "text-embedding",
- "features": null,
- "fetch_from": "predefined-model",
- "model_properties": {
- "context_size": 8192
- },
- "deprecated": false,
- "status": "active",
- "load_balancing_enabled": false
- },
- {
- "model": "text_embedding",
- "label": {
- "zh_Hans": "text_embedding",
- "en_US": "text_embedding"
- },
- "model_type": "text-embedding",
- "features": null,
- "fetch_from": "predefined-model",
- "model_properties": {
- "context_size": 512
- },
- "deprecated": false,
- "status": "active",
- "load_balancing_enabled": false
- }
- ]
- }
- ]
- }
- ```
- </CodeGroup>
- </Col>
</Row>
<hr className='ml-0 mr-0' />
--
Gitblit v1.8.0