Viewing the Chunks After Document Parsing

Function

View the current document and the chunk list after document parsing, including details about each chunk.

URI

GET /v1/{project_id}/applications/{application_id}/uni-search/files/{file_id}/docs

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Definition: Project ID. For details about how to obtain the project ID, see Obtaining a Project ID. Constraints: N/A Value range: The value can contain 1 to 64 characters. Only digits, letters, hyphens (-), and underscores (_) are allowed. The value must start with a letter. Default value: N/A
application_id	Yes	String	Definition: Application ID. For details about how to obtain the application ID, see Obtaining an Application ID. Constraints: Character string Value range: The value can contain 1 to 64 characters. Only digits, letters, hyphens (-), and underscores (_) are allowed. The value must start with a letter. Default value: N/A
file_id	Yes	String	Definition: File ID. Constraints: N/A Value range: Length: 1 to 64 characters. The value can contain only digits, letters, hyphens (-), and underscores (_). Default value: N/A

**Table 2** Query Parameters
Parameter	Mandatory	Type	Description
page_size	No	Integer	Definition: Number of records displayed on each page, indicating the number of records returned per request. The default value is 10, indicating that 10 records are displayed on each page. Constraints: N/A Value range: 1-65535 Default value: 10
page_num	No	Integer	Definition: Page number of the current request, indicating the start page from data retrieval. The default value is 1, indicating to start from the first page. Constraints: N/A Value range: 1-65535 Default value: 1
file_type	No	String	Definition: File type. The value can contain a maximum of 64 characters. Constraints: N/A Value range: N/A Default value: N/A
repo_id	No	String	Definition: Knowledge base ID. When carried in the request, it specifies the target knowledge base for the query. Constraints: N/A Value range: N/A Default value: N/A

Request Parameters

**Table 3** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Definition: Token used for API authentication. For details about how to obtain the token, see Obtaining an IAM User Token. Constraints: N/A Value range: N/A Default value: N/A

Response Parameters

Status code: 200

**Table 4** Response body parameters
Parameter	Type	Description
docs	Array of FileDocInfo objects	Definition: File segment list. Value range: N/A
page_num	Long	Definition: Page number in the request. Value range: N/A
page_size	Long	Definition: Page size in the request. Value range: N/A
total	Long	Definition: Total number of segments. Value range: N/A
version	Integer	Definition: Version information. Value range: N/A

**Table 5** FileDocInfo
Parameter	Type	Description
id	String	Definition: Chunk ID. Value range: N/A
timestamp	String	Definition: Segment creation timestamp. To ensure proper display of segment data, this field is not updated along with the segment data. Value range: N/A
title	String	Definition: Segment title. Value range: N/A
content	String	Definition: Segment content. Value range: N/A
page_num	Long	Definition: Segment page number, which is not involved in FAQ segment content. Value range: N/A
page_num_list	Array of longs	Definition: Segment page number. When the file type is PDF, a single segment can contain multiple pages. Value range: N/A
component_num	Long	Definition: Segment content sequence number, which is not involved in FAQ fragment content. Value range: N/A
element_id	String	Definition: File element ID. Value range: N/A
elements	Array of strings	Definition: Data element in HTML. Value range: N/A Constraints: This parameter is supported only in clusters 25.7.T1 or later.
pdf_coordinate	Object	Definition: Metadata used for locating text during PDF parsing. Example value: [ [ 202, 687 ], [ 1031, 687 ] ] Value range: N/A Constraints: This parameter is supported only in clusters 25.7.T1 or later.

Status code: 404

**Table 6** Response body parameters
Parameter	Type	Description
error_code	String	Definition: Error Code. Value range: N/A
error_msg	String	Definition: Error message. Value range: N/A

Example Requests

View document chunks after parsing.

/v1/b25446daeb1a41a7953c5deba2b2677a/applications/cefb2a59-2f9e-4268-b56b-eab15dc0b9d6/uni-search/files/6c95aa82c4f0bb509e30fa017874101b/docs?page_size=10&file_type=pdf&page_num=1

Example Responses

Status code: 200

Query response body.

{
  "page_num" : 1,
  "page_size" : 1,
  "total" : 1,
  "docs" : [ {
    "id" : "065c6b2f47354b3797e14d1e6a013a7e",
    "timestamp" : "1745827606521",
    "title" : "Global Accelerator Billing",
    "content" : "Pay-per-use: It is a postpaid model where payment is made after usage, and billing is based on the actual usage duration of the acceleration instance. For details, see Billing Modes.\nBilling items",
    "page_num" : 1,
    "component_num" : 1
  } ],
  "version" : 1
}