Uploading Documents

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

repo_id

Yes

String

Definition:

Knowledge base ID.

How to obtain:

Log in to the KooSearch experience platform. In the navigation tree on the left, choose Knowledge Bases to view knowledge base IDs. Each knowledge base has a unique ID stored in the vector database.

Constraints:

N/A

Value range:

Length: 1 to 64 characters. The value can contain only digits, letters, hyphens (-), and underscores (_).

Default value:

N/A

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

file

Yes

File

Definition:

File to be uploaded.

Constraints:

Supported document formats are as follows: .doc, .docx, .pdf, .pptx, .ppt, .xlsx, .xls, .csv, .wps, .png, .jpg, .jpeg, .bmp, .gif, .tiff, .tif, .webp, .pcx, .ico, .psd, .dps, .et, .txt, .ofd, .md. Multiple documents can be uploaded at once. The size of each single document cannot exceed 128 MB. (Upload a document through an API if its size exceeds 60 MB.)

Value range:

N/A

Default value:

N/A

category

No

String

Definition:

Document directory, which corresponds to the leaf nodes in the directory tree. This parameter has only one value.

The recommended format is "leaf node directory name (directory ID)", for example, patent (3166-1).

Constraints:

N/A

Value range:

N/A

Default value:

N/A

tags

No

Array of strings

Definition:

Document tags. You can use tags to automatically group documents for filtering.

Constraints:

In 25.2.T1, the following special characters are allowed in URLs: :/.?&=@#%+~!$'(),;*[]

Precautions:

1. You are advised to use case-insensitive tags. For example, 'Approved' and 'approved' are the same tag.

2. A document can have more than one tag.

Value range:

The value can contain 1 to 255 characters. It can only contain letters, digits, and the following special characters: : - _ / . ? & = @ # / %+ ~ ! $ ' ( ) , ; *[]. The value must start with a letter or digit.

Default value:

N/A

file_extract_req

No

String

Definition:

Document-level parsing parameters. For details, see FileExtractTaskReq.

Example

{"mode":1,"language":"CHINESE","parse_conf":{"ocr_enabled":true," mllm_model":"mllm6","image_enabled":true,"image_conf":"IMAGE","header_footer_enabled":false," footnote_enabled":false,"catalog_enabled":false},"split_conf":{"split_mode":"RULE","chunk_size":500,"separators":[". ",".","! ","!","? ","?"],"title_level":3,"combine_title":true,"merge_titles":true,"rule_regexs":["^Chapter ([1-9]{1,7})","^Section ([1-9]{1,7}),"^Clause([1-9]{1,7})"]}}.

Constraints:

For details about the structure, see FileExtractTaskReq.

Value range:

N/A

Default value:

N/A

chat_id

No

String

Definition:

Chat ID.

Constraints:

N/A

Value range:

The maximum length is 64 characters.

Default value:

N/A

file_id

String

Definition:

Document ID.

Value range:

N/A

error_code

String

Definition:

Error Code.

Value range:

N/A

error_msg

String

Definition:

Error message.

Value range:

N/A

error_code

String

Definition:

Error Code.

Value range:

N/A

error_msg

String

Definition:

Error message.

Value range:

N/A

201

Response body of the API for uploading documents.

400

Incorrect request body parameter.

500

Internal error.