Miscellaneous updates to session APIs (#4097)

### What problem does this PR solve?



### Type of change


- [x] Documentation Update

---------

Co-authored-by: Kevin Hu <[email protected]>

docs/references/http_api_reference.md

@@ -9,19 +9,17 @@ A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure
 
 ---
 
-:::tip API GROUPING
-Dataset Management
-:::
+## DATASET MANAGEMENT
 
 ---
 
-## Create dataset
+### Create dataset
 
 **POST** `/api/v1/datasets`
 
 Creates a dataset.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/datasets`
@@ -38,7 +36,7 @@ Creates a dataset.
   - `"chunk_method"`: `string`
   - `"parser_config"`: `object`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -50,7 +48,7 @@ curl --request POST \
       }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `"name"`: (*Body parameter*), `string`, *Required*  
   The unique name of the dataset to create. It must adhere to the following requirements:  
@@ -114,7 +112,7 @@ curl --request POST \
     - `"delimiter"`: Defaults to `"\n!?。；！？"`.
     - `"entity_types"`: Defaults to `["organization","person","location","event","time"]`
 
-### Response
+#### Response
 
 Success:
 
@@ -166,13 +164,13 @@ Failure:
 
 ---
 
-## Delete datasets
+### Delete datasets
 
 **DELETE** `/api/v1/datasets`
 
 Deletes datasets by ID.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/datasets`
@@ -182,7 +180,7 @@ Deletes datasets by ID.
   - Body:
     - `"ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request DELETE \
@@ -194,12 +192,12 @@ curl --request DELETE \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `"ids"`: (*Body parameter*), `list[string]`  
   The IDs of the datasets to delete. If it is not specified, all datasets will be deleted.
 
-### Response
+#### Response
 
 Success:
 
@@ -220,13 +218,13 @@ Failure:
 
 ---
 
-## Update dataset
+### Update dataset
 
 **PUT** `/api/v1/datasets/{dataset_id}`
 
 Updates configurations for a specified dataset.
 
-### Request
+#### Request
 
 - Method: PUT
 - URL: `/api/v1/datasets/{dataset_id}`
@@ -238,7 +236,7 @@ Updates configurations for a specified dataset.
   - `"embedding_model"`: `string`
   - `"chunk_method"`: `enum<string>`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request PUT \
@@ -251,7 +249,7 @@ curl --request PUT \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The ID of the dataset to update.
@@ -276,7 +274,7 @@ curl --request PUT \
   - `"knowledge_graph"`: Knowledge Graph  
     Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
 
-### Response
+#### Response
 
 Success:
 
@@ -297,20 +295,20 @@ Failure:
 
 ---
 
-## List datasets
+### List datasets
 
 **GET** `/api/v1/datasets?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
 
 Lists datasets.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/datasets?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -318,7 +316,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `page`: (*Filter parameter*)  
   Specifies the page on which the datasets will be displayed. Defaults to `1`.
@@ -335,7 +333,7 @@ curl --request GET \
 - `id`: (*Filter parameter*)  
   The ID of the dataset to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -391,19 +389,17 @@ Failure:
 
 ---
 
-:::tip API GROUPING
-File Management within Dataset
-:::
+## FILE MANAGEMENT WITHIN DATASET
 
 ---
 
-## Upload documents
+### Upload documents
 
 **POST** `/api/v1/datasets/{dataset_id}/documents`
 
 Uploads documents to a specified dataset.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/datasets/{dataset_id}/documents`
@@ -413,7 +409,7 @@ Uploads documents to a specified dataset.
 - Form:
   - `'file=@{FILE_PATH}'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -424,14 +420,14 @@ curl --request POST \
      --form 'file=@./test2.pdf'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The ID of the dataset to which the documents will be uploaded.
 - `'file'`: (*Body parameter*)  
   A document to upload.
 
-### Response
+#### Response
 
 Success:
 
@@ -475,13 +471,13 @@ Failure:
 
 ---
 
-## Update document
+### Update document
 
 **PUT** `/api/v1/datasets/{dataset_id}/documents/{document_id}`
 
 Updates configurations for a specified document.
 
-### Request
+#### Request
 
 - Method: PUT
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}`
@@ -493,7 +489,7 @@ Updates configurations for a specified document.
   - `"chunk_method"`:`string`
   - `"parser_config"`:`object`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request PUT \
@@ -509,7 +505,7 @@ curl --request PUT \
 
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The ID of the associated dataset.
@@ -548,7 +544,7 @@ curl --request PUT \
     - `"delimiter"`: Defaults to `"\n!?。；！？"`.
     - `"entity_types"`: Defaults to `["organization","person","location","event","time"]`
 
-### Response
+#### Response
 
 Success:
 
@@ -569,13 +565,13 @@ Failure:
 
 ---
 
-## Download document
+### Download document
 
 **GET** `/api/v1/datasets/{dataset_id}/documents/{document_id}`
 
 Downloads a document from a specified dataset.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}`
@@ -584,7 +580,7 @@ Downloads a document from a specified dataset.
 - Output:
   - `'{PATH_TO_THE_FILE}'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -593,14 +589,14 @@ curl --request GET \
      --output ./ragflow.txt
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
 - `documents_id`: (*Path parameter*)  
   The ID of the document to download.
 
-### Response
+#### Response
 
 Success:
 
@@ -619,13 +615,13 @@ Failure:
 
 ---
 
-## List documents
+### List documents
 
 **GET** `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}`
 
 Lists documents in a specified dataset.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}`
@@ -633,7 +629,7 @@ Lists documents in a specified dataset.
   - `'content-Type: application/json'`
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -641,7 +637,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
@@ -660,7 +656,7 @@ curl --request GET \
 - `id`: (*Filter parameter*), `string`  
   The ID of the document to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -716,13 +712,13 @@ Failure:
 
 ---
 
-## Delete documents
+### Delete documents
 
 **DELETE** `/api/v1/datasets/{dataset_id}/documents`
 
 Deletes documents by ID.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/datasets/{dataset_id}/documents`
@@ -732,7 +728,7 @@ Deletes documents by ID.
 - Body:
   - `"ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request DELETE \
@@ -745,14 +741,14 @@ curl --request DELETE \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
 - `"ids"`: (*Body parameter*), `list[string]`  
   The IDs of the documents to delete. If it is not specified, all documents in the specified dataset will be deleted.
 
-### Response
+#### Response
 
 Success:
 
@@ -773,13 +769,13 @@ Failure:
 
 ---
 
-## Parse documents
+### Parse documents
 
 **POST** `/api/v1/datasets/{dataset_id}/chunks`
 
 Parses documents in a specified dataset.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/datasets/{dataset_id}/chunks`
@@ -789,7 +785,7 @@ Parses documents in a specified dataset.
 - Body:
   - `"document_ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -802,14 +798,14 @@ curl --request POST \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The dataset ID.
 - `"document_ids"`: (*Body parameter*), `list[string]`, *Required*  
   The IDs of the documents to parse.
 
-### Response
+#### Response
 
 Success:
 
@@ -830,13 +826,13 @@ Failure:
 
 ---
 
-## Stop parsing documents
+### Stop parsing documents
 
 **DELETE** `/api/v1/datasets/{dataset_id}/chunks`
 
 Stops parsing specified documents.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/datasets/{dataset_id}/chunks`
@@ -846,7 +842,7 @@ Stops parsing specified documents.
 - Body:
   - `"document_ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request DELETE \
@@ -859,14 +855,14 @@ curl --request DELETE \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
 - `"document_ids"`: (*Body parameter*), `list[string]`, *Required*  
   The IDs of the documents for which the parsing should be stopped.
 
-### Response
+#### Response
 
 Success:
 
@@ -887,13 +883,13 @@ Failure:
 
 ---
 
-## Add chunk
+### Add chunk
 
 **POST** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
 
 Adds a chunk to a specified document in a specified dataset.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
@@ -904,7 +900,7 @@ Adds a chunk to a specified document in a specified dataset.
   - `"content"`: `string`
   - `"important_keywords"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -917,7 +913,7 @@ curl --request POST \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
@@ -928,7 +924,7 @@ curl --request POST \
 - `"important_keywords`(*Body parameter*), `list[string]`  
   The key terms or phrases to tag with the chunk.
 
-### Response
+#### Response
 
 Success:
 
@@ -962,20 +958,20 @@ Failure:
 
 ---
 
-## List chunks
+### List chunks
 
 **GET** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks?keywords={keywords}&page={page}&page_size={page_size}&id={id}`
 
 Lists chunks in a specified document.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks?keywords={keywords}&page={page}&page_size={page_size}&id={chunk_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -983,7 +979,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>' 
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
@@ -998,7 +994,7 @@ curl --request GET \
 - `id`(*Filter parameter*), `string`  
   The ID of the chunk to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -1069,13 +1065,13 @@ Failure:
 
 ---
 
-## Delete chunks
+### Delete chunks
 
 **DELETE** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
 
 Deletes chunks by ID.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks`
@@ -1085,7 +1081,7 @@ Deletes chunks by ID.
 - Body:
   - `"chunk_ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request DELETE \
@@ -1098,7 +1094,7 @@ curl --request DELETE \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
@@ -1107,7 +1103,7 @@ curl --request DELETE \
 - `"chunk_ids"`: (*Body parameter*), `list[string]`  
   The IDs of the chunks to delete. If it is not specified, all chunks of the specified document will be deleted.
 
-### Response
+#### Response
 
 Success:
 
@@ -1128,13 +1124,13 @@ Failure:
 
 ---
 
-## Update chunk
+### Update chunk
 
 **PUT** `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks/{chunk_id}`
 
 Updates content or configurations for a specified chunk.
 
-### Request
+#### Request
 
 - Method: PUT
 - URL: `/api/v1/datasets/{dataset_id}/documents/{document_id}/chunks/{chunk_id}`
@@ -1146,7 +1142,7 @@ Updates content or configurations for a specified chunk.
   - `"important_keywords"`: `list[string]`
   - `"available"`: `boolean`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request PUT \
@@ -1160,7 +1156,7 @@ curl --request PUT \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `dataset_id`: (*Path parameter*)  
   The associated dataset ID.
@@ -1177,7 +1173,7 @@ curl --request PUT \
   - `true`: Available (default)
   - `false`: Unavailable
 
-### Response
+#### Response
 
 Success:
 
@@ -1198,13 +1194,13 @@ Failure:
 
 ---
 
-## Retrieve chunks
+### Retrieve chunks
 
 **POST** `/api/v1/retrieval`
 
 Retrieves chunks from specified datasets.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/retrieval`
@@ -1224,7 +1220,7 @@ Retrieves chunks from specified datasets.
   - `"keyword"`: `boolean`  
   - `"highlight"`: `boolean`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -1239,7 +1235,7 @@ curl --request POST \
      }'
 ```
 
-#### Request parameter
+##### Request parameter
 
 - `"question"`: (*Body parameter*), `string`, *Required*  
   The user query or query keywords.
@@ -1268,7 +1264,7 @@ curl --request POST \
   - `true`: Enable highlighting of matched terms.
   - `false`: Disable highlighting of matched terms (default).
 
-### Response
+#### Response
 
 Success:
 
@@ -1320,19 +1316,17 @@ Failure:
 
 ---
 
-:::tip API GROUPING
-Chat Assistant Management
-:::
+## CHAT ASSISTANT MANAGEMENT
 
 ---
 
-## Create chat assistant
+### Create chat assistant
 
 **POST** `/api/v1/chats`
 
 Creates a chat assistant.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/chats`
@@ -1346,7 +1340,7 @@ Creates a chat assistant.
   - `"llm"`: `object`
   - `"prompt"`: `object`
 
-#### Request example
+##### Request example
 
 ```shell
 curl --request POST \
@@ -1359,7 +1353,7 @@ curl --request POST \
 }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `"name"`: (*Body parameter*), `string`, *Required*  
   The name of the chat assistant.
@@ -1396,7 +1390,7 @@ curl --request POST \
   - `"show_quote`: `boolean` Indicates whether the source of text should be displayed. Defaults to `true`.
   - `"prompt"`: `string` The prompt content.
 
-### Response
+#### Response
 
 Success:
 
@@ -1459,13 +1453,13 @@ Failure:
 
 ---
 
-## Update chat assistant
+### Update chat assistant
 
 **PUT** `/api/v1/chats/{chat_id}`
 
 Updates configurations for a specified chat assistant.
 
-### Request
+#### Request
 
 - Method: PUT
 - URL: `/api/v1/chats/{chat_id}`
@@ -1479,7 +1473,7 @@ Updates configurations for a specified chat assistant.
   - `"llm"`: `object`
   - `"prompt"`: `object`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request PUT \
@@ -1531,7 +1525,7 @@ curl --request PUT \
   - `"show_quote`: `boolean` Indicates whether the source of text should be displayed. Defaults to `true`.
   - `"prompt"`: `string` The prompt content.
 
-### Response
+#### Response
 
 Success:
 
@@ -1552,13 +1546,13 @@ Failure:
 
 ---
 
-## Delete chat assistants
+### Delete chat assistants
 
 **DELETE** `/api/v1/chats`
 
 Deletes chat assistants by ID.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/chats`
@@ -1568,7 +1562,7 @@ Deletes chat assistants by ID.
 - Body:
   - `"ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request DELETE \
@@ -1581,12 +1575,12 @@ curl --request DELETE \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `"ids"`: (*Body parameter*), `list[string]`  
   The IDs of the chat assistants to delete. If it is not specified, all chat assistants in the system will be deleted.
 
-### Response
+#### Response
 
 Success:
 
@@ -1607,20 +1601,20 @@ Failure:
 
 ---
 
-## List chat assistants
+### List chat assistants
 
 **GET** `/api/v1/chats?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={chat_name}&id={chat_id}`
 
 Lists chat assistants.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/chats?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -1628,7 +1622,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `page`: (*Filter parameter*), `integer`  
   Specifies the page on which the chat assistants will be displayed. Defaults to `1`.
@@ -1645,7 +1639,7 @@ curl --request GET \
 - `name`: (*Filter parameter*), `string`  
   The name of the chat assistant to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -1706,13 +1700,19 @@ Failure:
 }
 ```
 
-## Create session with chat assistant
+---
+
+## CHAT SESSIONS
+
+---
+
+### Create session with chat assistant
 
 **POST** `/api/v1/chats/{chat_id}/sessions`
 
 Creates a session with a chat assistant.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/chats/{chat_id}/sessions`
@@ -1722,7 +1722,7 @@ Creates a session with a chat assistant.
 - Body:
   - `"name"`: `string`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -1735,14 +1735,14 @@ curl --request POST \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `chat_id`: (*Path parameter*)  
   The ID of the associated chat assistant.
 - `"name"`: (*Body parameter*), `string`  
   The name of the chat session to create.
 
-### Response
+#### Response
 
 Success:
 
@@ -1778,13 +1778,13 @@ Failure:
 
 ---
 
-## Update session
+### Update session
 
 **PUT** `/api/v1/chats/{chat_id}/sessions/{session_id}`
 
 Updates a session of a specified chat assistant.
 
-### Request
+#### Request
 
 - Method: PUT
 - URL: `/api/v1/chats/{chat_id}/sessions/{session_id}`
@@ -1794,7 +1794,7 @@ Updates a session of a specified chat assistant.
 - Body:
   - `"name`: `string`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request PUT \
@@ -1807,7 +1807,7 @@ curl --request PUT \
      }'
 ```
 
-#### Request Parameter
+##### Request Parameter
 
 - `chat_id`: (*Path parameter*)  
   The ID of the associated chat assistant.
@@ -1816,7 +1816,7 @@ curl --request PUT \
 - `"name"`: (*Body Parameter), `string`  
   The revised name of the session.
 
-### Response
+#### Response
 
 Success:
 
@@ -1837,20 +1837,20 @@ Failure:
 
 ---
 
-## List sessions
+### List sessions
 
 **GET** `/api/v1/chats/{chat_id}/sessions?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={session_name}&id={session_id}`
 
 Lists sessions associated with a specified chat assistant.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/chats/{chat_id}/sessions?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={session_name}&id={session_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -1858,7 +1858,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request Parameters
+##### Request Parameters
 
 - `chat_id`: (*Path parameter*)  
   The ID of the associated chat assistant.
@@ -1877,7 +1877,7 @@ curl --request GET \
 - `id`: (*Filter parameter*), `string`  
   The ID of the chat session to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -1915,13 +1915,13 @@ Failure:
 
 ---
 
-## Delete sessions
+### Delete sessions
 
 **DELETE** `/api/v1/chats/{chat_id}/sessions`
 
 Deletes sessions of a chat assistant by ID.
 
-### Request
+#### Request
 
 - Method: DELETE
 - URL: `/api/v1/chats/{chat_id}/sessions`
@@ -1931,10 +1931,9 @@ Deletes sessions of a chat assistant by ID.
 - Body:
   - `"ids"`: `list[string]`
 
-#### Request example
+##### Request example
 
 ```bash
-# Either id or name must be provided, but not both.
 curl --request DELETE \
      --url http://{address}/api/v1/chats/{chat_id}/sessions \
      --header 'Content-Type: application/json' \
@@ -1945,14 +1944,14 @@ curl --request DELETE \
      }'
 ```
 
-#### Request Parameters
+##### Request Parameters
 
 - `chat_id`: (*Path parameter*)  
   The ID of the associated chat assistant.
 - `"ids"`: (*Body Parameter*), `list[string]`  
   The IDs of the sessions to delete. If it is not specified, all sessions associated with the specified chat assistant will be deleted.
 
-### Response
+#### Response
 
 Success:
 
@@ -1973,7 +1972,7 @@ Failure:
 
 ---
 
-## Converse with chat assistant
+### Converse with chat assistant
 
 **POST** `/api/v1/chats/{chat_id}/completions`
 
@@ -1994,7 +1993,7 @@ Asks a specified chat assistant a question to start an AI-powered conversation.
 
 :::
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/chats/{chat_id}/completions`
@@ -2006,7 +2005,7 @@ Asks a specified chat assistant a question to start an AI-powered conversation.
   - `"stream"`: `boolean`
   - `"session_id"`: `string`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -2029,7 +2028,8 @@ curl --request POST \
           "session_id":"9fa7691cb85c11ef9c5f0242ac120005"
      }'
 ```
-#### Request Parameters
+
+##### Request Parameters
 
 - `chat_id`: (*Path parameter*)  
   The ID of the associated chat assistant.
@@ -2042,7 +2042,8 @@ curl --request POST \
 - `"session_id"`: (*Body Parameter*)  
   The ID of session. If it is not provided, a new session will be generated.
 
-### Response
+#### Response
+
 Success without `session_id`:
 ```text
 data:{
@@ -2148,15 +2149,13 @@ Failure:
 
 ---
 
-## Create session with agent
-
-*If there are parameters in the `begin` component, the session cannot be created in this way.*
+### Create session with agent
 
 **POST** `/api/v1/agents/{agent_id}/sessions`
 
 Creates a session with an agent.
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/agents/{agent_id}/sessions`
@@ -2165,7 +2164,7 @@ Creates a session with an agent.
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 - Body:
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -2176,12 +2175,12 @@ curl --request POST \
      }'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `agent_id`: (*Path parameter*)  
   The ID of the associated agent assistant.
 
-### Response
+#### Response
 
 Success:
 
@@ -2299,7 +2298,7 @@ Failure:
 
 ---
 
-## Converse with agent
+### Converse with agent
 
 **POST** `/api/v1/agents/{agent_id}/completions`  
 
@@ -2320,7 +2319,7 @@ Asks a specified agent a question to start an AI-powered conversation.
 
 :::
 
-### Request
+#### Request
 
 - Method: POST
 - URL: `/api/v1/agents/{agent_id}/completions`
@@ -2332,7 +2331,7 @@ Asks a specified agent a question to start an AI-powered conversation.
   - `"stream"`: `boolean`
   - `"session_id"`: `string`
   - other parameters: `string`
-#### Request example
+##### Request example
 
 ```bash
 curl --request POST \
@@ -2368,7 +2367,7 @@ curl --request POST \
 ```
 
 
-#### Request Parameters
+##### Request Parameters
 
 - `agent_id`: (*Path parameter*), `string`  
   The ID of the associated agent assistant.
@@ -2382,7 +2381,7 @@ curl --request POST \
   The ID of the session. If it is not provided, a new session will be generated.
 - Other parameters: (*Body Parameter*)  
   The parameters in the begin component.
-### Response
+#### Response
 success without `session_id` provided and with no parameters in the `begin` component:
 ```text
 data:{
@@ -2600,20 +2599,20 @@ Failure:
 
 ---
 
-## List agent sessions
+### List agent sessions
 
 **GET** `/api/v1/agents/{agent_id}/sessions?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&id={session_id}`
 
 Lists sessions associated with a specified agent.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/agents/{agent_id}/sessions?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&id={session_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -2621,7 +2620,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request Parameters
+##### Request Parameters
 
 - `agent_id`: (*Path parameter*)  
   The ID of the associated agent.
@@ -2638,7 +2637,7 @@ curl --request GET \
 - `id`: (*Filter parameter*), `string`  
   The ID of the agent session to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -2789,21 +2788,23 @@ Failure:
     "message": "You don't own the agent ccd2f856b12311ef94ca0242ac1200052."
 }
 ```
+
 ---
-## List agents
+
+### List agents
 
 **GET** `/api/v1/agents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={agent_name}&id={agent_id}`
 
 Lists agents.
 
-### Request
+#### Request
 
 - Method: GET
 - URL: `/api/v1/agents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={agent_name}&id={agent_id}`
 - Headers:
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-#### Request example
+##### Request example
 
 ```bash
 curl --request GET \
@@ -2811,7 +2812,7 @@ curl --request GET \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
-#### Request parameters
+##### Request parameters
 
 - `page`: (*Filter parameter*), `integer`  
   Specifies the page on which the agents will be displayed. Defaults to `1`.
@@ -2828,7 +2829,7 @@ curl --request GET \
 - `name`: (*Filter parameter*), `string`  
   The name of the agent to retrieve.
 
-### Response
+#### Response
 
 Success:
 
@@ -2897,4 +2898,6 @@ Failure:
     "code": 102,
     "message": "The agent doesn't exist."
 }
-```
+```
+
+---

docs/references/python_api_reference.md

@@ -7,22 +7,21 @@ slug: /python_api_reference
 
 A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](https://ragflow.io/docs/dev/acquire_ragflow_api_key).
 
----
+:::tip NOTE
+Run the following command to download the Python SDK:
 
-:::tip API GROUPING
-Dataset Management
+```bash
+pip install ragflow-sdk
+```
 :::
 
 ---
-### Install the RAGFlow SDK
 
-To install the RAGFlow SDK, run the following command in your terminal:
+## DATASET MANAGEMENT
 
-```bash
-pip install ragflow-sdk
-```
+---
 
-## Create dataset
+### Create dataset
 
 ```python
 RAGFlow.create_dataset(
@@ -39,9 +38,9 @@ RAGFlow.create_dataset(
 
 Creates a dataset.
 
-### Parameters
+#### Parameters
 
-#### name: `str`, *Required*
+##### name: `str`, *Required*
 
 The unique name of the dataset to create. It must adhere to the following requirements:
 
@@ -53,29 +52,29 @@ The unique name of the dataset to create. It must adhere to the following requir
 - Maximum 65,535 characters.
 - Case-insensitive.
 
-#### avatar: `str`
+##### avatar: `str`
 
 Base64 encoding of the avatar. Defaults to `""`
 
-#### description: `str`
+##### description: `str`
 
 A brief description of the dataset to create. Defaults to `""`.
 
-#### language: `str`
+##### language: `str`
 
 The language setting of the dataset to create. Available options:
 
 - `"English"` (default)
 - `"Chinese"`
 
-#### permission
+##### permission
 
 Specifies who can access the dataset to create. Available options:  
 
 - `"me"`: (Default) Only you can manage the dataset.
 - `"team"`: All team members can manage the dataset.
 
-#### chunk_method, `str`
+##### chunk_method, `str`
 
 The chunking method of the dataset to create. Available options:
 
@@ -93,7 +92,7 @@ The chunking method of the dataset to create. Available options:
   Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
 - `"email"`: Email
 
-#### parser_config
+##### parser_config
 
 The parser configuration of the dataset. A `ParserConfig` object's attributes vary based on the selected `chunk_method`:
 
@@ -122,12 +121,12 @@ The parser configuration of the dataset. A `ParserConfig` object's attributes va
 - `chunk_method`=`"email"`:  
   `None`
 
-### Returns
+#### Returns
 
 - Success: A `dataset` object.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -138,7 +137,7 @@ dataset = rag_object.create_dataset(name="kb_1")
 
 ---
 
-## Delete datasets
+### Delete datasets
 
 ```python
 RAGFlow.delete_datasets(ids: list[str] = None)
@@ -146,18 +145,18 @@ RAGFlow.delete_datasets(ids: list[str] = None)
 
 Deletes datasets by ID.
 
-### Parameters
+#### Parameters
 
-#### ids: `list[str]`, *Required*
+##### ids: `list[str]`, *Required*
 
 The IDs of the datasets to delete. Defaults to `None`. If it is not specified, all datasets will be deleted.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 rag_object.delete_datasets(ids=["id_1","id_2"])
@@ -165,7 +164,7 @@ rag_object.delete_datasets(ids=["id_1","id_2"])
 
 ---
 
-## List datasets
+### List datasets
 
 ```python
 RAGFlow.list_datasets(
@@ -180,50 +179,50 @@ RAGFlow.list_datasets(
 
 Lists datasets.
 
-### Parameters
+#### Parameters
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the datasets will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The number of datasets on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The field by which datasets should be sorted. Available options:
 
 - `"create_time"` (default)
 - `"update_time"`
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved datasets should be sorted in descending order. Defaults to `True`.
 
-#### id: `str`
+##### id: `str`
 
 The ID of the dataset to retrieve. Defaults to `None`.
 
-#### name: `str`
+##### name: `str`
 
 The name of the dataset to retrieve. Defaults to `None`.
 
-### Returns
+#### Returns
 
 - Success: A list of `DataSet` objects.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
-#### List all datasets
+##### List all datasets
 
 ```python
 for dataset in rag_object.list_datasets():
     print(dataset)
 ```
 
-#### Retrieve a dataset by ID
+##### Retrieve a dataset by ID
 
 ```python
 dataset = rag_object.list_datasets(id = "id_1")
@@ -232,7 +231,7 @@ print(dataset[0])
 
 ---
 
-## Update dataset
+### Update dataset
 
 ```python
 DataSet.update(update_message: dict)
@@ -240,9 +239,9 @@ DataSet.update(update_message: dict)
 
 Updates configurations for the current dataset.
 
-### Parameters
+#### Parameters
 
-#### update_message: `dict[str, str|int]`, *Required*
+##### update_message: `dict[str, str|int]`, *Required*
 
 A dictionary representing the attributes to update, with the following keys:
 
@@ -264,12 +263,12 @@ A dictionary representing the attributes to update, with the following keys:
   - `"knowledge_graph"`: Knowledge Graph  
     Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -281,13 +280,11 @@ dataset.update({"embedding_model":"BAAI/bge-zh-v1.5", "chunk_method":"manual"})
 
 ---
 
-:::tip API GROUPING
-File Management within Dataset
-:::
+## FILE MANAGEMENT WITHIN DATASET
 
 ---
 
-## Upload documents
+### Upload documents
 
 ```python
 DataSet.upload_documents(document_list: list[dict])
@@ -295,21 +292,21 @@ DataSet.upload_documents(document_list: list[dict])
 
 Uploads documents to the current dataset.
 
-### Parameters
+#### Parameters
 
-#### document_list: `list[dict]`, *Required*
+##### document_list: `list[dict]`, *Required*
 
 A list of dictionaries representing the documents to upload, each containing the following keys:
 
 - `"display_name"`: (Optional) The file name to display in the dataset.  
 - `"blob"`: (Optional) The binary content of the file to upload.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 dataset = rag_object.create_dataset(name="kb_name")
@@ -318,7 +315,7 @@ dataset.upload_documents([{"display_name": "1.txt", "blob": "<BINARY_CONTENT_OF_
 
 ---
 
-## Update document
+### Update document
 
 ```python
 Document.update(update_message:dict)
@@ -326,9 +323,9 @@ Document.update(update_message:dict)
 
 Updates configurations for the current document.
 
-### Parameters
+#### Parameters
 
-#### update_message: `dict[str, str|dict[]]`, *Required*
+##### update_message: `dict[str, str|dict[]]`, *Required*
 
 A dictionary representing the attributes to update, with the following keys:
 
@@ -373,12 +370,12 @@ A dictionary representing the attributes to update, with the following keys:
   - `chunk_method`=`"email"`:  
     `None`
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -393,7 +390,7 @@ doc.update([{"parser_config": {"chunk_token_count": 256}}, {"chunk_method": "man
 
 ---
 
-## Download document
+### Download document
 
 ```python
 Document.download() -> bytes
@@ -401,11 +398,11 @@ Document.download() -> bytes
 
 Downloads the current document.
 
-### Returns
+#### Returns
 
 The downloaded document in bytes.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -421,7 +418,7 @@ print(doc)
 
 ---
 
-## List documents
+### List documents
 
 ```python
 Dataset.list_documents(id:str =None, keywords: str=None, page: int=1, page_size:int = 30, order_by:str = "create_time", desc: bool = True) -> list[Document]
@@ -429,36 +426,36 @@ Dataset.list_documents(id:str =None, keywords: str=None, page: int=1, page_size:
 
 Lists documents in the current dataset.
 
-### Parameters
+#### Parameters
 
-#### id: `str`
+##### id: `str`
 
 The ID of the document to retrieve. Defaults to `None`.
 
-#### keywords: `str`
+##### keywords: `str`
 
 The keywords used to match document titles. Defaults to `None`.
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the documents will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The maximum number of documents on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The field by which documents should be sorted. Available options:
 
 - `"create_time"` (default)
 - `"update_time"`
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved documents should be sorted in descending order. Defaults to `True`.
 
-### Returns
+#### Returns
 
 - Success: A list of `Document` objects.
 - Failure: `Exception`.
@@ -513,7 +510,7 @@ A `Document` object contains the following attributes:
   - `chunk_method`=`"email"`:  
     `None`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -530,7 +527,7 @@ for doc in dataset.list_documents(keywords="rag", page=0, page_size=12):
 
 ---
 
-## Delete documents
+### Delete documents
 
 ```python
 DataSet.delete_documents(ids: list[str] = None)
@@ -538,18 +535,18 @@ DataSet.delete_documents(ids: list[str] = None)
 
 Deletes documents by ID.
 
-### Parameters
+#### Parameters
 
-#### ids: `list[list]`
+##### ids: `list[list]`
 
 The IDs of the documents to delete. Defaults to `None`. If it is not specified, all documents in the dataset will be deleted.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -562,7 +559,7 @@ dataset.delete_documents(ids=["id_1","id_2"])
 
 ---
 
-## Parse documents
+### Parse documents
 
 ```python
 DataSet.async_parse_documents(document_ids:list[str]) -> None
@@ -570,18 +567,18 @@ DataSet.async_parse_documents(document_ids:list[str]) -> None
 
 Parses documents in the current dataset.
 
-### Parameters
+#### Parameters
 
-#### document_ids: `list[str]`, *Required*
+##### document_ids: `list[str]`, *Required*
 
 The IDs of the documents to parse.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
@@ -602,7 +599,7 @@ print("Async bulk parsing initiated.")
 
 ---
 
-## Stop parsing documents
+### Stop parsing documents
 
 ```python
 DataSet.async_cancel_parse_documents(document_ids:list[str])-> None
@@ -610,18 +607,18 @@ DataSet.async_cancel_parse_documents(document_ids:list[str])-> None
 
 Stops parsing specified documents.
 
-### Parameters
+#### Parameters
 
-#### document_ids: `list[str]`, *Required*
+##### document_ids: `list[str]`, *Required*
 
 The IDs of the documents for which parsing should be stopped.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
@@ -644,7 +641,7 @@ print("Async bulk parsing cancelled.")
 
 ---
 
-## Add chunk
+### Add chunk
 
 ```python
 Document.add_chunk(content:str, important_keywords:list[str] = []) -> Chunk
@@ -652,17 +649,17 @@ Document.add_chunk(content:str, important_keywords:list[str] = []) -> Chunk
 
 Adds a chunk to the current document.
 
-### Parameters
+#### Parameters
 
-#### content: `str`, *Required*
+##### content: `str`, *Required*
 
 The text content of the chunk.
 
-#### important_keywords: `list[str]`
+##### important_keywords: `list[str]`
 
 The key terms or phrases to tag with the chunk.
 
-### Returns
+#### Returns
 
 - Success: A `Chunk` object.
 - Failure: `Exception`.
@@ -681,8 +678,7 @@ A `Chunk` object contains the following attributes:
   - `False`: Unavailable
   - `True`: Available (default)
 
-
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -697,7 +693,7 @@ chunk = doc.add_chunk(content="xxxxxxx")
 
 ---
 
-## List chunks
+### List chunks
 
 ```python
 Document.list_chunks(keywords: str = None, page: int = 1, page_size: int = 30, id : str = None) -> list[Chunk]
@@ -705,30 +701,30 @@ Document.list_chunks(keywords: str = None, page: int = 1, page_size: int = 30, i
 
 Lists chunks in the current document.
 
-### Parameters
+#### Parameters
 
-#### keywords: `str`
+##### keywords: `str`
 
 The keywords used to match chunk content. Defaults to `None`
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the chunks will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The maximum number of chunks on each page. Defaults to `30`.
 
-#### id: `str`
+##### id: `str`
 
 The ID of the chunk to retrieve. Default: `None`
 
-### Returns
+#### Returns
 
 - Success: A list of `Chunk` objects.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -743,7 +739,7 @@ for chunk in doc.list_chunks(keywords="rag", page=0, page_size=12):
 
 ---
 
-## Delete chunks
+### Delete chunks
 
 ```python
 Document.delete_chunks(chunk_ids: list[str])
@@ -751,18 +747,18 @@ Document.delete_chunks(chunk_ids: list[str])
 
 Deletes chunks by ID.
 
-### Parameters
+#### Parameters
 
-#### chunk_ids: `list[str]`
+##### chunk_ids: `list[str]`
 
 The IDs of the chunks to delete. Defaults to `None`. If it is not specified, all chunks of the current document will be deleted.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -778,7 +774,7 @@ doc.delete_chunks(["id_1","id_2"])
 
 ---
 
-## Update chunk
+### Update chunk
 
 ```python
 Chunk.update(update_message: dict)
@@ -786,9 +782,9 @@ Chunk.update(update_message: dict)
 
 Updates content or configurations for the current chunk.
 
-### Parameters
+#### Parameters
 
-#### update_message: `dict[str, str|list[str]|int]` *Required*
+##### update_message: `dict[str, str|list[str]|int]` *Required*
 
 A dictionary representing the attributes to update, with the following keys:
 
@@ -798,12 +794,12 @@ A dictionary representing the attributes to update, with the following keys:
   - `False`: Unavailable
   - `True`: Available (default)
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -819,7 +815,7 @@ chunk.update({"content":"sdfx..."})
 
 ---
 
-## Retrieve chunks
+### Retrieve chunks
 
 ```python
 RAGFlow.retrieve(question:str="", dataset_ids:list[str]=None, document_ids=list[str]=None, page:int=1, page_size:int=30, similarity_threshold:float=0.2, vector_similarity_weight:float=0.3, top_k:int=1024,rerank_id:str=None,keyword:bool=False,higlight:bool=False) -> list[Chunk]
@@ -827,64 +823,64 @@ RAGFlow.retrieve(question:str="", dataset_ids:list[str]=None, document_ids=list[
 
 Retrieves chunks from specified datasets.
 
-### Parameters
+#### Parameters
 
-#### question: `str`, *Required*
+##### question: `str`, *Required*
 
 The user query or query keywords. Defaults to `""`.
 
-#### dataset_ids: `list[str]`, *Required*
+##### dataset_ids: `list[str]`, *Required*
 
 The IDs of the datasets to search. Defaults to `None`. If you do not set this argument, ensure that you set `document_ids`.
 
-#### document_ids: `list[str]`
+##### document_ids: `list[str]`
 
 The IDs of the documents to search. Defaults to `None`. You must ensure all selected documents use the same embedding model. Otherwise, an error will occur. If you do not set this argument, ensure that you set `dataset_ids`.
 
-#### page: `int`
+##### page: `int`
 
 The starting index for the documents to retrieve. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The maximum number of chunks to retrieve. Defaults to `30`.
 
-#### Similarity_threshold: `float`
+##### Similarity_threshold: `float`
 
 The minimum similarity score. Defaults to `0.2`.
 
-#### vector_similarity_weight: `float`
+##### vector_similarity_weight: `float`
 
 The weight of vector cosine similarity. Defaults to `0.3`. If x represents the vector cosine similarity, then (1 - x) is the term similarity weight.
 
-#### top_k: `int`
+##### top_k: `int`
 
 The number of chunks engaged in vector cosine computaton. Defaults to `1024`.
 
-#### rerank_id: `str`
+##### rerank_id: `str`
 
 The ID of the rerank model. Defaults to `None`.
 
-#### keyword: `bool`
+##### keyword: `bool`
 
 Indicates whether to enable keyword-based matching:
 
 - `True`: Enable keyword-based matching.
 - `False`: Disable keyword-based matching (default).
 
-#### highlight: `bool`
+##### highlight: `bool`
 
 Specifies whether to enable highlighting of matched terms in the results:
 
 - `True`: Enable highlighting of matched terms.
 - `False`: Disable highlighting of matched terms (default).
 
-### Returns
+#### Returns
 
 - Success: A list of `Chunk` objects representing the document chunks.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -909,13 +905,11 @@ for c in rag_object.retrieve(question="What's ragflow?",
 
 ---
 
-:::tip API GROUPING
-Chat Assistant Management
-:::
+## CHAT ASSISTANT MANAGEMENT
 
 ---
 
-## Create chat assistant
+### Create chat assistant
 
 ```python
 RAGFlow.create_chat(
@@ -929,21 +923,21 @@ RAGFlow.create_chat(
 
 Creates a chat assistant.
 
-### Parameters
+#### Parameters
 
-#### name: `str`, *Required*
+##### name: `str`, *Required*
 
 The name of the chat assistant.
 
-#### avatar: `str`
+##### avatar: `str`
 
 Base64 encoding of the avatar. Defaults to `""`.
 
-#### dataset_ids: `list[str]`
+##### dataset_ids: `list[str]`
 
 The IDs of the associated datasets. Defaults to `[""]`.
 
-#### llm: `Chat.LLM`
+##### llm: `Chat.LLM`
 
 The LLM settings for the chat assistant to create. Defaults to `None`. When the value is `None`, a dictionary with the following values will be generated as the default. An `LLM` object contains the following attributes:
 
@@ -960,7 +954,7 @@ The LLM settings for the chat assistant to create. Defaults to `None`. When the
 - `max_token`: `int`  
   The maximum length of the model's output, measured in the number of tokens (words or pieces of words). Defaults to `512`. If disabled, you lift the maximum token limit, allowing the model to determine the number of tokens in its responses.
 
-#### prompt: `Chat.Prompt`
+##### prompt: `Chat.Prompt`
 
 Instructions for the LLM to follow.  A `Prompt` object contains the following attributes:
 
@@ -977,12 +971,12 @@ Instructions for the LLM to follow.  A `Prompt` object contains the following at
 - `show_quote`: `bool` Indicates whether the source of text should be displayed. Defaults to `True`.
 - `prompt`: `str` The prompt content.
 
-### Returns
+#### Returns
 
 - Success: A `Chat` object representing the chat assistant.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -997,7 +991,7 @@ assistant = rag_object.create_chat("Miss R", dataset_ids=dataset_ids)
 
 ---
 
-## Update chat assistant
+### Update chat assistant
 
 ```python
 Chat.update(update_message: dict)
@@ -1005,9 +999,9 @@ Chat.update(update_message: dict)
 
 Updates configurations for the current chat assistant.
 
-### Parameters
+#### Parameters
 
-#### update_message: `dict[str, str|list[str]|dict[]]`, *Required*
+##### update_message: `dict[str, str|list[str]|dict[]]`, *Required*
 
 A dictionary representing the attributes to update, with the following keys:
 
@@ -1035,12 +1029,12 @@ A dictionary representing the attributes to update, with the following keys:
   - `"show_quote`: `bool` Indicates whether the source of text should be displayed Defaults to `True`.
   - `"prompt"`: `str` The prompt content.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1054,7 +1048,7 @@ assistant.update({"name": "Stefan", "llm": {"temperature": 0.8}, "prompt": {"top
 
 ---
 
-## Delete chat assistants
+### Delete chat assistants
 
 ```python
 RAGFlow.delete_chats(ids: list[str] = None)
@@ -1062,18 +1056,18 @@ RAGFlow.delete_chats(ids: list[str] = None)
 
 Deletes chat assistants by ID.
 
-### Parameters
+#### Parameters
 
-#### ids: `list[str]`
+##### ids: `list[str]`
 
 The IDs of the chat assistants to delete. Defaults to `None`. If it is empty or not specified, all chat assistants in the system will be deleted.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1084,7 +1078,7 @@ rag_object.delete_chats(ids=["id_1","id_2"])
 
 ---
 
-## List chat assistants
+### List chat assistants
 
 ```python
 RAGFlow.list_chats(
@@ -1099,41 +1093,41 @@ RAGFlow.list_chats(
 
 Lists chat assistants.
 
-### Parameters
+#### Parameters
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the chat assistants will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The number of chat assistants on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The attribute by which the results are sorted. Available options:
 
 - `"create_time"` (default)
 - `"update_time"`
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved chat assistants should be sorted in descending order. Defaults to `True`.
 
-#### id: `str`  
+##### id: `str`  
 
 The ID of the chat assistant to retrieve. Defaults to `None`.
 
-#### name: `str`  
+##### name: `str`  
 
 The name of the chat assistant to retrieve. Defaults to `None`.
 
-### Returns
+#### Returns
 
 - Success: A list of `Chat` objects.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1145,13 +1139,11 @@ for assistant in rag_object.list_chats():
 
 ---
 
-:::tip API GROUPING
-Chat Session APIs
-:::
+## CHAT SESSIONS
 
 ---
 
-## Create session with chat assistant
+### Create session with chat assistant
 
 ```python
 Chat.create_session(name: str = "New session") -> Session
@@ -1159,22 +1151,22 @@ Chat.create_session(name: str = "New session") -> Session
 
 Creates a session with the current chat assistant.
 
-### Parameters
+#### Parameters
 
-#### name: `str`
+##### name: `str`
 
 The name of the chat session to create.
 
-### Returns
+#### Returns
 
 - Success: A `Session` object containing the following attributes:
   - `id`: `str` The auto-generated unique identifier of the created session.
   - `name`: `str` The name of the created session.
-  - `message`: `list[Message]` The messages of the created session assistant. Default: `[{"role": "assistant", "content": "Hi! I am your assistant，can I help you?"}]`
+  - `message`: `list[Message]` The opening message of the created session. Default: `[{"role": "assistant", "content": "Hi! I am your assistant，can I help you?"}]`
   - `chat_id`: `str` The ID of the associated chat assistant.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1187,7 +1179,7 @@ session = assistant.create_session()
 
 ---
 
-## Update chat assistant's session
+### Update chat assistant's session
 
 ```python
 Session.update(update_message: dict)
@@ -1195,20 +1187,20 @@ Session.update(update_message: dict)
 
 Updates the current session of the current chat assistant.
 
-### Parameters
+#### Parameters
 
-#### update_message: `dict[str, Any]`, *Required*
+##### update_message: `dict[str, Any]`, *Required*
 
 A dictionary representing the attributes to update, with only one key:
 
 - `"name"`: `str` The revised name of the session.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1222,7 +1214,7 @@ session.update({"name": "updated_name"})
 
 ---
 
-## List chat assistant's sessions
+### List chat assistant's sessions
 
 ```python
 Chat.list_sessions(
@@ -1237,41 +1229,41 @@ Chat.list_sessions(
 
 Lists sessions associated with the current chat assistant.
 
-### Parameters
+#### Parameters
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the sessions will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The number of sessions on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The field by which sessions should be sorted. Available options:
 
 - `"create_time"` (default)
 - `"update_time"`
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved sessions should be sorted in descending order. Defaults to `True`.
 
-#### id: `str`
+##### id: `str`
 
 The ID of the chat session to retrieve. Defaults to `None`.
 
-#### name: `str`
+##### name: `str`
 
 The name of the chat session to retrieve. Defaults to `None`.
 
-### Returns
+#### Returns
 
 - Success: A list of `Session` objects associated with the current chat assistant.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1285,7 +1277,7 @@ for session in assistant.list_sessions():
 
 ---
 
-## Delete chat assistant's sessions
+### Delete chat assistant's sessions
 
 ```python
 Chat.delete_sessions(ids:list[str] = None)
@@ -1293,18 +1285,18 @@ Chat.delete_sessions(ids:list[str] = None)
 
 Deletes sessions of the current chat assistant by ID.
 
-### Parameters
+#### Parameters
 
-#### ids: `list[str]`
+##### ids: `list[str]`
 
 The IDs of the sessions to delete. Defaults to `None`. If it is not specified, all sessions associated with the current chat assistant will be deleted.
 
-### Returns
+#### Returns
 
 - Success: No value is returned.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1317,7 +1309,7 @@ assistant.delete_sessions(ids=["id_1","id_2"])
 
 ---
 
-## Converse with chat assistant
+### Converse with chat assistant
 
 ```python
 Session.ask(question: str, stream: bool = False) -> Optional[Message, iter[Message]]
@@ -1329,35 +1321,35 @@ Asks a specified chat assistant a question to start an AI-powered conversation.
 In streaming mode, not all responses include a reference, as this depends on the system's judgement.
 :::
 
-### Parameters
+#### Parameters
 
-#### question: `str`, *Required*
+##### question: `str`, *Required*
 
 The question to start an AI-powered conversation.
 
-#### stream: `bool`
+##### stream: `bool`
 
 Indicates whether to output responses in a streaming way:
 
 - `True`: Enable streaming (default).
 - `False`: Disable streaming.
 
-### Returns
+#### Returns
 
-- A `Message` object containing the response to the question if `stream` is set to `False`
+- A `Message` object containing the response to the question if `stream` is set to `False`.
 - An iterator containing multiple `message` objects (`iter[Message]`) if `stream` is set to `True`
 
 The following shows the attributes of a `Message` object:
 
-#### id: `str`
+##### id: `str`
 
 The auto-generated message ID.
 
-#### content: `str`
+##### content: `str`
 
 The content of the message. Defaults to `"Hi! I am your assistant, can I help you?"`.
 
-#### reference: `list[Chunk]`
+##### reference: `list[Chunk]`
 
 A list of `Chunk` objects representing references to the message, each containing the following attributes:
 
@@ -1382,7 +1374,7 @@ A list of `Chunk` objects representing references to the message, each containin
 - `term_similarity` `float`  
   A keyword similarity score of the chunk ranging from `0` to `1`, with a higher value indicating greater similarity between keywords.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1407,15 +1399,15 @@ while True:
 
 ---
 
-## Create session with agent
-*If there are parameters in the `begin` component, the session cannot be created in this way.*
+### Create session with agent
+
 ```python
 Agent.create_session(id,rag) -> Session
 ```
 
-Creates a  session with the current agent.
+Creates a session with the current agent.
 
-### Returns
+#### Returns
 
 - Success: A `Session` object containing the following attributes:
   - `id`: `str` The auto-generated unique identifier of the created session.
@@ -1423,7 +1415,7 @@ Creates a  session with the current agent.
   - `agent_id`: `str` The ID of the associated agent assistant.
 - Failure: `Exception`
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1435,7 +1427,7 @@ session = create_session(AGENT_ID,rag_object)
 
 ---
 
-## Converse with agent
+### Converse with agent
 
 ```python
 Session.ask(question: str, stream: bool = False) -> Optional[Message, iter[Message]]
@@ -1447,35 +1439,35 @@ Asks a specified agent a question to start an AI-powered conversation.
 In streaming mode, not all responses include a reference, as this depends on the system's judgement.
 :::
 
-### Parameters
+#### Parameters
 
-#### question: `str`, *Required*
+##### question: `str`, *Required*
 
 The question to start an AI-powered conversation.
 
-#### stream: `bool`
+##### stream: `bool`
 
 Indicates whether to output responses in a streaming way:
 
 - `True`: Enable streaming (default).
 - `False`: Disable streaming.
 
-### Returns
+#### Returns
 
 - A `Message` object containing the response to the question if `stream` is set to `False`
 - An iterator containing multiple `message` objects (`iter[Message]`) if `stream` is set to `True`
 
 The following shows the attributes of a `Message` object:
 
-#### id: `str`
+##### id: `str`
 
 The auto-generated message ID.
 
-#### content: `str`
+##### content: `str`
 
 The content of the message. Defaults to `"Hi! I am your assistant, can I help you?"`.
 
-#### reference: `list[Chunk]`
+##### reference: `list[Chunk]`
 
 A list of `Chunk` objects representing references to the message, each containing the following attributes:
 
@@ -1500,7 +1492,7 @@ A list of `Chunk` objects representing references to the message, each containin
 - `term_similarity` `float`  
   A keyword similarity score of the chunk ranging from `0` to `1`, with a higher value indicating greater similarity between keywords.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow,Agent
@@ -1521,9 +1513,10 @@ while True:
         print(ans.content[len(cont):], end='', flush=True)
         cont = ans.content
 ```
+
 ---
 
-## List agent sessions
+### List agent sessions
 
 ```python
 Agent.list_sessions(
@@ -1539,38 +1532,37 @@ Agent.list_sessions(
 
 Lists sessions associated with the current agent.
 
-### Parameters
+#### Parameters
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the sessions will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The number of sessions on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The field by which sessions should be sorted. Available options:
 
 - `"create_time"`
 - `"update_time"`(default)
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved sessions should be sorted in descending order. Defaults to `True`.
 
-#### id: `str`
+##### id: `str`
 
 The ID of the agent session to retrieve. Defaults to `None`.
 
-
-### Returns
+#### Returns
 
 - Success: A list of `Session` objects associated with the current agent.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
@@ -1583,7 +1575,8 @@ for session in sessions:
 ```
 
 ---
-## List agents
+
+### List agents
 
 ```python
 RAGFlow.list_agents(
@@ -1598,45 +1591,47 @@ RAGFlow.list_agents(
 
 Lists agents.
 
-### Parameters
+#### Parameters
 
-#### page: `int`
+##### page: `int`
 
 Specifies the page on which the agents will be displayed. Defaults to `1`.
 
-#### page_size: `int`
+##### page_size: `int`
 
 The number of agents on each page. Defaults to `30`.
 
-#### orderby: `str`
+##### orderby: `str`
 
 The attribute by which the results are sorted. Available options:
 
 - `"create_time"` (default)
 - `"update_time"`
 
-#### desc: `bool`
+##### desc: `bool`
 
 Indicates whether the retrieved agents should be sorted in descending order. Defaults to `True`.
 
-#### id: `str`  
+##### id: `str`  
 
 The ID of the agent to retrieve. Defaults to `None`.
 
-#### name: `str`  
+##### name: `str`  
 
 The name of the agent to retrieve. Defaults to `None`.
 
-### Returns
+#### Returns
 
 - Success: A list of `Agent` objects.
 - Failure: `Exception`.
 
-### Examples
+#### Examples
 
 ```python
 from ragflow_sdk import RAGFlow
 rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
 for agent in rag_object.list_agents():
     print(agent)
-```
+```
+
+---