Create a Document Parsing Task

project_id

Yes

String

Definition:

Specifies the 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

app_id

Yes

String

Definition:

Application ID. For details about how to obtain the application ID, see Obtaining an Application ID.

Constraints:

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

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_path

Yes

String

Definition:

Path of the document uploaded to OBS. Only one document can be uploaded each time.

Constraints:

N/A

Value range:

N/A

Default value:

N/A

language

No

String

Definition:

Document language. The options are zh (Chinese), en (English), ar (Arabic), th (Thai), pt (Portuguese), and es (Spanish). This parameter is optional for Chinese and English documents.

Constraints:

N/A

Value range:

Options:

• es

• ar

• pt

• th

• en

• zh

Default value:

N/A

mode

No

Integer

Definition:

Document splitting mode.

Constraints:

N/A

Value range:

1-4

Default value:

N/A

ocr

No

Boolean

Definition:

Whether to use OCR for document parsing.

Constraints:

N/A

Value range:

• false: Do not use OCR parsing.

• true: Use OCR parsing.

Default value:

N/A

priority

No

Integer

Definition:

Task priority. A larger value indicates a higher priority.

Constraints:

N/A

Value range:

N/A

Default value:

N/A

parse_conf

No

DocParseConfig object

Definition:

Document parsing configuration.

Constraints:

N/A

Value range:

N/A

Default value:

N/A

split_conf

No

DocSplitConfig object

Definition:

Text splitting configuration.

Constraints:

N/A

Value range:

N/A

Default value:

N/A

ocr_enabled

No

Boolean

Definition:

Whether to use OCR for document parsing.

Constraints:

N/A

Value range:

• true: Use OCR parsing.

• false: Do not use OCR parsing.

Default value:

N/A

mllm_enabled

No

Boolean

Definition:

Whether to use multi-modal parsing.

Constraints:

N/A

Value range:

• true: Use multi-modal parsing.

• false: Do not use multi-modal parsing.

Default value:

N/A

image_conf

No

String

Definition:

Image parsing mode. TEXT: Extracts text from the image. IMAGE: Retains the original image. IMAGE_TEXT: Extracts the text and retains the original image.

Constraints:

N/A

Value range:

Options:

• TEXT: Extracts text from the image.

• IMAGE: Retains the original image.

• IMAGE_TEXT: Extracts the text and retains the original image.

Default value:

TEXT

image_enabled

No

Boolean

Definition:

Whether to parse images.

Constraints:

N/A

Value range:

• true: Parse images.

• false: Do not parse images.

Default value:

N/A

header_footer_enabled

No

Boolean

Definition:

Whether to parse page headers and footers.

Constraints:

N/A

Value range:

• true: Parse headers and footers.

• false: Do not parse headers and footers.

Default value:

N/A

catalog_enabled

No

Boolean

Definition:

Whether to parse directories.

Constraints:

N/A

Value range:

• true: Parse directories.

• false: Not to parse directories.

Default value:

N/A

footnote_enabled

No

Boolean

Definition:

Whether to parse footnotes.

Constraints:

N/A

Value range:

• true: Parse footnotes.

• false: Do not parse footnotes.

Default value:

N/A

mllm_model

No

String

Definition:

Whether to use multi-modal parsing. Multiple multi-modal models can be configured and matched by name.

Constraints:

N/A

Value range:

1 to 32 characters

Default value:

N/A

mllm_prompt

No

Map<String,String>

Definition:

Multi-modal prompt.

Constraints:

N/A

Value range:

N/A

Default value:

N/A

split_mode

No

String

Definition:

Text splitting mode.

Value range:

• LENGTH: Split by word count.

• CATALOG: Split by Contents.

• RULE: Split by rule.

• AUTO: automatic.

separators

No

Array of strings

Definition:

Paragraph separator.

Value range:

N/A

chunk_size

No

Integer

Definition:

Maximum chunk length.

Value range:

N/A

overlap

No

Float

Definition:

Chunk overlap ratio.

Value range:

N/A

title_level

No

Integer

Definition:

Maximum title depth.

Value range:

N/A

combine_title

No

Boolean

Definition:

Whether to merge titles. Merged format: title 1 title 2 title 3. Non-merged format: title 3.

Value range:

N/A

rule_regexs

No

Array of strings

Title matching expression in the rule splitting scenario.

merge_titles

No

Boolean

Whether to merge paragraphs. When enabled, small paragraphs will be merged.

task_id

String

Definition:

ID of a document parsing task. You can use this ID to query the document parsing progress and result.

Value range:

N/A

error_code

String

Definition:

Error code

Value range:

N/A

error_msg

String

Definition:

Error description

Value range:

N/A

error_code

String

Definition:

Error code

Value range:

N/A

error_msg

String

Definition:

Error description

Value range:

N/A

error_code

String

Definition:

Error code

Value range:

N/A

error_msg

String

Definition:

Error description

Value range:

N/A

200

File content parsing task creation result

400

Request parameter error

401

Authentication exception

500

Internal error